© 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. 20594
    Prev
    Next
    INDEX
    Explanations

    technical terms related to digital formats and access methods

    oai_token-act-pair · gpt-3.5-turbo

    references to various digital formats for sharing and accessing content

    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
    enery
    -0.65
    ukong
    -0.64
     Killed
    -0.63
    define
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    enario
    -0.60
    reated
    -0.58
     Inher
    -0.58
    Neg
    -0.56
    appiness
    -0.56
    POSITIVE LOGITS
     archive
    1.09
     archives
    0.90
     Scrib
    0.88
     publication
    0.88
     reader
    0.86
     archived
    0.84
     publishing
    0.83
     publish
    0.83
     reprint
    0.82
     editor
    0.78
    Activations Density 1.487%

    No Known Activations