© 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. 8-RES-JB
    11. 6176
    Prev
    Next
    INDEX
    Explanations

    numbers representing percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical ranges associated with income levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warts
    -0.77
    agan
    -0.71
    anced
    -0.71
    verend
    -0.70
    abol
    -0.68
     symmetry
    -0.67
    ancing
    -0.66
    swick
    -0.65
    arial
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     MHz
    1.02
    px
    0.93
    MHz
    0.93
    Hz
    0.88
    +
    0.87
     meters
    0.85
    mAh
    0.85
     metres
    0.85
    +.
    0.84
     Mile
    0.82
    Activations Density 0.074%

    No Known Activations