© 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. 7-RES-JB
    11. 13389
    Prev
    Next
    INDEX
    Explanations

    phrases related to affiliate links and potential earnings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of affiliate links and related disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pist
    -0.73
     Fam
    -0.69
    naire
    -0.68
     Eug
    -0.68
    Reloaded
    -0.66
    etts
    -0.64
    lyak
    -0.64
     Rampage
    -0.63
     pont
    -0.63
     Proced
    -0.62
    POSITIVE LOGITS
    iframe
    0.77
    yright
    0.76
     content
    0.75
     cookies
    0.75
    iliate
    0.73
    content
    0.72
     permissions
    0.70
     transcription
    0.70
     {*
    0.69
     attribution
    0.69
    Activations Density 0.297%

    No Known Activations