© 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. 1-RES-JB
    11. 9393
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and names of companies or products often used in a professional context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology partnerships and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.53
     looph
    -0.52
     wounding
    -0.51
     exting
    -0.51
     Prosecut
    -0.50
     treason
    -0.49
    judicial
    -0.48
     hating
    -0.48
     rebell
    -0.48
     Reconstruction
    -0.47
    POSITIVE LOGITS
    irection
    0.59
    ocument
    0.57
    erella
    0.49
    trace
    0.48
    tyard
    0.47
    glers
    0.46
    irect
    0.44
    uable
    0.44
    izont
    0.43
    itionally
    0.43
    Activations Density 6.335%

    No Known Activations