© 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. 1-RES-JB
    11. 9419
    Prev
    Next
    INDEX
    Explanations

    words related to skimming or going through something quickly

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and related verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Afgh
    -0.71
    CVE
    -0.70
    BOOK
    -0.64
    DEV
    -0.64
    sword
    -0.63
    better
    -0.60
    cv
    -0.58
    aceae
    -0.58
    ²¾
    -0.57
     fry
    -0.57
    POSITIVE LOGITS
    imming
    1.17
    tsky
    0.85
    orph
    0.79
    etitive
    0.79
    odies
    0.76
    igree
    0.75
    immers
    0.74
    acing
    0.74
    bles
    0.73
     Pool
    0.73
    Activations Density 0.013%

    No Known Activations