© 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. 2795
    Prev
    Next
    INDEX
    Explanations

    webpage sign-up prompts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up or subscriptions

    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
    mith
    -0.93
    clair
    -0.82
    enth
    -0.73
    matter
    -0.72
    nil
    -0.71
    odynamics
    -0.71
    heim
    -0.70
    loo
    -0.70
    illin
    -0.70
    chem
    -0.70
    POSITIVE LOGITS
     membership
    0.85
     captcha
    0.79
     renewal
    0.76
     instance
    0.76
     confirmation
    0.71
     free
    0.69
     participation
    0.69
     grabs
    0.69
     perpet
    0.68
     premium
    0.68
    Activations Density 0.045%

    No Known Activations