© 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. 3703
    Prev
    Next
    INDEX
    Explanations

    visual descriptions of how things appear

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or appearance

    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
    kson
    -0.77
    wu
    -0.73
    âĹ¼
    -0.73
    verend
    -0.71
    venient
    -0.70
    essional
    -0.70
    iling
    -0.70
    learning
    -0.69
    umbn
    -0.69
    ricular
    -0.69
    POSITIVE LOGITS
     suspic
    0.76
    ahead
    0.71
    bones
    0.69
    ynt
    0.69
    ãĤ¶
    0.68
     shif
    0.68
     unbeat
    0.67
     noses
    0.64
     awfully
    0.64
     suspicious
    0.64
    Activations Density 0.058%

    No Known Activations