© 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. 0-RES-JB
    11. 20325
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a negative or unpleasant situation

    oai_token-act-pair · gpt-3.5-turbo

    words associated with a bleak or serious tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Promotion
    -0.72
    division
    -0.72
    bats
    -0.72
    leave
    -0.71
    deals
    -0.71
     divor
    -0.69
    flo
    -0.69
     Seym
    -0.67
     indu
    -0.67
    oi
    -0.66
    POSITIVE LOGITS
     grim
    2.94
     Grim
    1.87
    grim
    1.57
     gruesome
    1.35
     horrifying
    1.01
     improvised
    0.99
     harrowing
    0.95
     horrific
    0.95
     grun
    0.94
     grit
    0.92
    Activations Density 0.034%

    No Known Activations