© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14908
    Prev
    Next
    INDEX
    Explanations

    words related to technological advancements and industry, especially in the context of motion pictures and transportation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of entertainment and performance media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.81
    EStreamFrame
    -0.79
    isSpecialOrderable
    -0.79
    ,,,,
    -0.77
    andestine
    -0.76
     Helpful
    -0.75
    REDACTED
    -0.73
    uliffe
    -0.72
     ABE
    -0.72
    Interstitial
    -0.70
    POSITIVE LOGITS
    -
    0.92
    âĢij
    0.81
    ops
    0.78
    tech
    0.74
    âĢIJ
    0.74
    cast
    0.71
     ray
    0.70
    war
    0.69
    ath
    0.68
    mat
    0.68
    Activations Density 0.819%

    No Known Activations