© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    references to rules, regulations, or standards

    oai_token-act-pair · gpt-3.5-turbo

    references to minimum requirements or standards

    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
    swick
    -0.78
    adel
    -0.76
    rious
    -0.73
    ãĥĪ
    -0.70
    CT
    -0.70
    herer
    -0.68
    lean
    -0.68
     Tid
    -0.66
     Camb
    -0.66
    riz
    -0.66
    POSITIVE LOGITS
     minimum
    1.09
     wage
    0.90
    minimum
    0.89
     amount
    0.88
     Minimum
    0.87
     penalties
    0.87
     disclosure
    0.84
     requirements
    0.81
     tolerated
    0.80
     wages
    0.79
    Activations Density 0.006%

    No Known Activations