© 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. 20220
    Prev
    Next
    INDEX
    Explanations

    plateau or crest-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stability and levels in various contexts

    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
    portation
    -0.75
    alez
    -0.69
    RH
    -0.64
    ilies
    -0.60
    att
    -0.58
    cas
    -0.58
    opal
    -0.58
    unal
    -0.58
    olly
    -0.58
    ĪĴ
    -0.58
    POSITIVE LOGITS
     plateau
    1.38
     peaks
    0.90
    fall
    0.76
    edIn
    0.76
     Wem
    0.73
     crest
    0.71
    zx
    0.71
    =-=-
    0.70
    hene
    0.68
     Archdemon
    0.68
    Activations Density 0.004%

    No Known Activations