© 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. 46064
    Prev
    Next
    INDEX
    Explanations

    news-related terms and words related to newsletters

    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
    167
    +0.05
    0.6%
    163
    +0.05
    0.6%
    326
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.05
    0.19
    326
    +0.05
    0.18
    744
    +0.04
    0.09
    Negative Logits
    esian
    -0.34
    sburgh
    -0.32
    igr
    -0.32
    fred
    -0.31
    thal
    -0.30
    gged
    -0.29
    ervation
    -0.29
    aged
    -0.29
    ini
    -0.28
    amer
    -0.28
    POSITIVE LOGITS
    LET
    0.43
    BOOK
    0.41
    £ı
    0.35
     BOX
    0.34
    KER
    0.34
     RELEASE
    0.33
     GEAR
    0.33
    è¦ļéĨĴ
    0.33
     LET
    0.32
    KING
    0.32
    Activations Density 5.454%

    No Known Activations