© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35048
    Prev
    Next
    INDEX
    Explanations

    words related to the character "Kavanna" and possibly related to a fantasy or magical world

    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
    288
    +0.16
    0.6%
    270
    +0.15
    0.6%
    343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.16
    0.10
    512
    +0.15
    0.07
    580
    +0.14
    0.08
    Negative Logits
    ©¶æ
    -0.93
    utenant
    -0.85
     phenomen
    -0.79
     defective
    -0.78
    sofar
    -0.77
     cooker
    -0.77
     trademark
    -0.77
    backer
    -0.77
     prone
    -0.76
     regress
    -0.76
    POSITIVE LOGITS
    irus
    1.65
    oided
    1.45
    ascular
    1.38
    atars
    1.36
    inelli
    1.35
    arro
    1.34
    itational
    1.33
    iew
    1.33
    ision
    1.32
    enture
    1.32
    Activations Density 8.914%

    No Known Activations