Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6871
    Prev
    Next
    INDEX
    Explanations

    URLs containing 'www', likely indicating a focus on website links

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "www" web address prefix

    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
     Ballard
    -0.81
     Courage
    -0.74
     Gillespie
    -0.74
    abal
    -0.65
    anooga
    -0.65
     Poles
    -0.65
    obyl
    -0.65
     Loans
    -0.65
     Chaff
    -0.62
    rained
    -0.62
    POSITIVE LOGITS
    www
    1.16
    natureconservancy
    0.98
    ww
    0.95
    youtube
    0.80
    hr
    0.79
    cms
    0.79
    twitter
    0.78
     www
    0.78
    ://
    0.77
    sites
    0.75
    Activations Density 0.007%

    No Known Activations