© 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. 34000
    Prev
    Next
    INDEX
    Explanations

    content related to skepticism or doubt

    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
    212
    +0.08
    0.4%
    748
    +0.08
    0.4%
    195
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.22
    357
    +0.08
    0.07
    67
    +0.08
    0.12
    Negative Logits
    olon
    -0.76
    brate
    -0.69
    brates
    -0.67
     Dome
    -0.63
    xual
    -0.62
    esville
    -0.61
     Kinnikuman
    -0.60
    è¦ļéĨĴ
    -0.59
     FIGHT
    -0.58
    å§«
    -0.58
    POSITIVE LOGITS
     legality
    0.77
     dubious
    0.72
    istry
    0.71
     suspic
    0.66
     questionable
    0.66
    CLASSIFIED
    0.59
    necess
    0.58
    iferation
    0.57
     skim
    0.57
     indisc
    0.57
    Activations Density 9.430%

    No Known Activations