© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or procedural discussions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and specifically commas in sentences

    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
    odes
    -0.64
    olves
    -0.63
    iary
    -0.60
    adelphia
    -0.60
    nih
    -0.60
    aukee
    -0.59
    ield
    -0.57
    ulz
    -0.57
    sect
    -0.56
    ighed
    -0.56
    POSITIVE LOGITS
     alas
    1.02
     albeit
    0.92
     although
    0.82
     however
    0.78
     moreover
    0.76
     unsurprisingly
    0.74
    maybe
    0.73
     etc
    0.73
     preferably
    0.73
    according
    0.73
    Activations Density 0.213%

    No Known Activations