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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 33275
    Prev
    Next
    INDEX
    Explanations

    details or instructions related to special designs or formulations

    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
    383
    +0.05
    0.6%
    251
    +0.04
    0.5%
    248
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.05
    0.19
    106
    +0.04
    0.11
    9
    +0.03
    0.10
    Negative Logits
     impossibility
    -0.28
     disbelief
    -0.28
     totality
    -0.27
     inev
    -0.27
    é¾
    -0.25
     dominance
    -0.24
     stagnation
    -0.23
    Õ
    -0.23
    nce
    -0.23
     trends
    -0.22
    POSITIVE LOGITS
     trained
    0.34
     tailored
    0.33
     fitted
    0.33
     specially
    0.32
     equipped
    0.32
     adapted
    0.31
    pecially
    0.31
     tuned
    0.30
     formulated
    0.30
     suited
    0.29
    Activations Density 6.039%

    No Known Activations