© 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. 15308
    Prev
    Next
    INDEX
    Explanations

    URLs and web domain names

    oai_token-act-pair · gpt-3.5-turbo

    references and details related to specific individuals and their professional affiliations or achievements

    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
     depended
    -0.53
     triv
    -0.50
     outwe
    -0.50
     outweigh
    -0.50
    Tokens
    -0.49
     justifies
    -0.49
     subjective
    -0.49
     depends
    -0.47
    glers
    -0.47
     disadvant
    -0.45
    POSITIVE LOGITS
    itone
    0.65
     himself
    0.59
     his
    0.56
     His
    0.53
    igl
    0.52
     Himself
    0.51
    reprene
    0.48
    itars
    0.48
    anky
    0.46
    NBA
    0.46
    Activations Density 2.851%

    No Known Activations