© 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. 11-RES-JB
    11. 15745
    Prev
    Next
    INDEX
    Explanations

    mentions related to newsletters or subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newsletters and email subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amiya
    -0.74
    nces
    -0.70
    ione
    -0.61
    mine
    -0.58
    nce
    -0.57
    ilial
    -0.57
     sear
    -0.57
    urn
    -0.56
    due
    -0.55
    rentice
    -0.55
    POSITIVE LOGITS
     daily
    0.64
    DragonMagazine
    0.63
    ãģĮ
    0.63
    cloneembedreportprint
    0.61
    erd
    0.60
    ãĤ¼
    0.59
    £ı
    0.59
    eva
    0.57
    anamo
    0.55
    arta
    0.55
    Activations Density 0.052%

    No Known Activations