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. 34492
    Prev
    Next
    INDEX
    Explanations

    words related to media, such as "media", "stream", "streaming", and "interview"

    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
    447
    +0.19
    0.9%
    288
    +0.15
    0.7%
    336
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.19
    0.07
    289
    +0.15
    -0.02
    360
    +0.12
    0.09
    Negative Logits
    ranch
    -0.76
    cker
    -0.70
    ģ«
    -0.69
    owsky
    -0.66
     Salvador
    -0.65
    0000000
    -0.65
    ãĤ¡
    -0.63
     Rasmussen
    -0.63
    bats
    -0.63
    lier
    -0.63
    POSITIVE LOGITS
    eval
    1.26
     outlets
    0.92
    wiki
    0.88
     mog
    0.78
     VIDEOS
    0.74
     literacy
    0.73
     playback
    0.73
     mogul
    0.71
     consolidation
    0.70
     outlet
    0.70
    Activations Density 8.258%

    No Known Activations