Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45446
    Prev
    Next
    INDEX
    Explanations

    text related to technical code and documentation

    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
    274
    +0.11
    0.6%
    743
    +0.11
    0.6%
    151
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.11
    0.18
    253
    +0.11
    0.15
    675
    +0.08
    0.15
    Negative Logits
    iller
    -0.72
    illing
    -0.60
     shortest
    -0.60
    annis
    -0.59
     Ott
    -0.57
     prevailing
    -0.56
     bod
    -0.54
     gast
    -0.54
    entimes
    -0.53
    onymous
    -0.53
    POSITIVE LOGITS
    **
    1.15
    ***
    1.15
    *****
    0.86
    @@@@@@@@
    0.82
    ###
    0.82
    ****
    0.82
    *.
    0.81
    ####
    0.79
    âĸĪâĸĪ
    0.78
    ============
    0.75
    Activations Density 4.181%

    No Known Activations