© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39433
    Prev
    Next
    INDEX
    Explanations

    words related to negative situations or emotions, particularly those with a prefix "un-"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    102
    +0.20
    0.8%
    616
    +0.20
    0.8%
    251
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.24
    616
    +0.20
    0.12
    745
    +0.14
    -0.12
    Negative Logits
    OPLE
    -0.96
     Dynamics
    -0.95
    anwhile
    -0.94
    ãĥ¼ãĥĨãĤ£
    -0.93
     briefs
    -0.91
    hetti
    -0.89
    jriwal
    -0.80
     Architecture
    -0.79
     Lauder
    -0.76
     sinks
    -0.75
    POSITIVE LOGITS
    balanced
    1.44
    ruly
    1.43
    assuming
    1.37
    apolog
    1.35
    organized
    1.35
    cles
    1.33
    confirmed
    1.32
    leased
    1.31
    availability
    1.29
    iting
    1.29
    Activations Density 11.799%

    No Known Activations