© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    words related to physical clothing or items people wear

    oai_token-act-pair · gpt-3.5-turbo

    references to wearing or conditions related to clothing and accessories

    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
    dem
    -0.70
    cedented
    -0.69
    gradient
    -0.68
    ancial
    -0.67
    skill
    -0.67
    aj
    -0.66
    fram
    -0.66
    izoph
    -0.65
    ctrl
    -0.65
    trade
    -0.65
    POSITIVE LOGITS
    earable
    0.71
    ×ķ
    0.69
     Hearth
    0.68
    perse
    0.67
    utical
    0.66
    avement
    0.65
    Buyable
    0.64
    CTV
    0.64
    IBLE
    0.62
     Beir
    0.62
    Activations Density 0.014%

    No Known Activations