© 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. 32573
    Prev
    Next
    INDEX
    Explanations

    words related to names or terms containing "onom" or "ism"

    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
    526
    +0.15
    0.7%
    271
    +0.12
    0.5%
    101
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.26
    683
    +0.12
    0.12
    154
    +0.11
    0.16
    Negative Logits
    FORE
    -0.72
    URN
    -0.69
    XXX
    -0.69
     Sail
    -0.67
     Inferno
    -0.66
    light
    -0.66
    LOAD
    -0.64
    ////////////////////////////////
    -0.64
    roads
    -0.63
     Rabbit
    -0.63
    POSITIVE LOGITS
    ical
    1.09
    ics
    1.04
    iotic
    1.02
    icon
    1.01
    iola
    1.00
    psey
    1.00
    icians
    0.98
    ically
    0.98
    icals
    0.97
    ophon
    0.94
    Activations Density 10.238%

    No Known Activations