© 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. 14801
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to web URLs

    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
    cffff
    -0.86
    ynski
    -0.82
    SPONSORED
    -0.74
    edient
    -0.73
    iaries
    -0.71
    hma
    -0.70
    rament
    -0.69
    ctuary
    -0.67
    romy
    -0.67
    manship
    -0.66
    POSITIVE LOGITS
     URL
    1.06
     URLs
    0.98
    URI
    0.97
    URL
    0.94
     url
    0.85
    Url
    0.82
     URI
    0.75
     encoded
    0.73
     prefix
    0.72
     hash
    0.70
    Activations Density 0.015%

    No Known Activations