© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20722
    Prev
    Next
    INDEX
    Explanations

    sources or references within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to sources of information or statements

    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
    TAG
    -0.73
    aeper
    -0.71
    osate
    -0.69
    eg
    -0.65
    Interstitial
    -0.64
    ĸļ
    -0.63
    eering
    -0.63
    Laun
    -0.63
    cair
    -0.62
    script
    -0.62
    POSITIVE LOGITS
     sources
    0.86
     informants
    0.83
     knowledgeable
    0.82
     priv
    0.81
     familiar
    0.78
     briefed
    0.77
     consulted
    0.73
     quoted
    0.71
    imate
    0.71
    iances
    0.70
    Activations Density 0.027%

    No Known Activations