© 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. 2-RES-JB
    11. 11064
    Prev
    Next
    INDEX
    Explanations

    words related to hyperlink references

    oai_token-act-pair · gpt-3.5-turbo

    references to hyperlinks or URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctic
    -0.69
     actionGroup
    -0.66
    urity
    -0.66
    mble
    -0.65
    apons
    -0.65
    rely
    -0.63
    oral
    -0.61
    thur
    -0.60
     proble
    -0.60
    ccording
    -0.59
    POSITIVE LOGITS
    edin
    1.49
    later
    1.11
    Link
    1.01
     Link
    0.99
     Links
    0.92
    link
    0.92
    ering
    0.84
    witz
    0.81
    ioned
    0.77
    edIn
    0.77
    Activations Density 0.007%

    No Known Activations