© 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. 24130
    Prev
    Next
    INDEX
    Explanations

    text related to introductions or introductory elements

    oai_token-act-pair · gpt-3.5-turbo

    references to "intro" and related terms 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
     Millennium
    -0.81
    UCK
    -0.66
    Trend
    -0.66
     Ivory
    -0.66
     Pharmaceutical
    -0.65
     BMC
    -0.63
     Chiefs
    -0.63
     Kingdoms
    -0.61
    VK
    -0.61
     Dying
    -0.61
    POSITIVE LOGITS
    spection
    1.73
    spective
    1.46
    verted
    1.40
    vert
    1.08
    verts
    1.07
    spect
    1.01
    version
    0.91
     Intro
    0.89
    jection
    0.87
    strings
    0.87
    Activations Density 0.006%

    No Known Activations