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

    Neuronpedia

    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. 19318
    Prev
    Next
    INDEX
    Explanations

    numbers related to electronics or technology specs

    oai_token-act-pair · gpt-3.5-turbo

    numeric data or values present in the text

    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
    nesday
    -0.80
    achus
    -0.74
    pire
    -0.72
     disadvant
    -0.72
     proble
    -0.71
    iya
    -0.67
    ushed
    -0.66
    pace
    -0.66
    lain
    -0.64
     McKenna
    -0.63
    POSITIVE LOGITS
    328
    1.06
    dfx
    1.00
     ILCS
    0.83
    otomy
    0.77
    obal
    0.76
    _-
    0.76
    GW
    0.73
    LECT
    0.72
    APS
    0.70
    _.
    0.69
    Activations Density 0.053%

    No Known Activations