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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4059
    Prev
    Next
    INDEX
    Explanations

    phrases related to culinary recipes

    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
    480
    +0.48
    4.9%
    87
    +0.36
    3.7%
    64
    +0.34
    3.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.48
    0.20
    480
    +0.36
    0.08
    464
    +0.34
    0.20
    Negative Logits
     respectively
    -0.31
    $.
    -0.29
    ]).
    -0.28
    Footnote
    -0.28
    Ire
    -0.27
    SPONSORED
    -0.26
    âĵĺ
    -0.26
    Interstitial
    -0.26
    senal
    -0.25
     mosqu
    -0.24
    POSITIVE LOGITS
     :=
    0.23
    reads
    0.21
    !:
    0.20
    own
    0.19
    acre
    0.19
     Fail
    0.19
    ren
    0.18
     START
    0.18
    bah
    0.18
     nutshell
    0.18
    Activations Density 3.278%

    No Known Activations