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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7338
    Prev
    Next
    INDEX
    Explanations

    phrases related to human society or the human condition

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments and references towards humanity

    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
    urations
    -0.81
    Bey
    -0.71
    stood
    -0.69
    FU
    -0.69
    olic
    -0.68
    Sym
    -0.64
     skim
    -0.64
    abet
    -0.62
    tein
    -0.62
     excerpts
    -0.62
    POSITIVE LOGITS
    ankind
    0.88
     beings
    0.86
     civilisation
    0.77
     humanity
    0.74
    icity
    0.73
     humankind
    0.73
     civilization
    0.68
    itably
    0.68
    idis
    0.68
     footprint
    0.67
    Activations Density 0.023%

    No Known Activations