© 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. 20847
    Prev
    Next
    INDEX
    Explanations

    names of specific publications or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific media outlets and publications

    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
    rine
    -0.76
    gur
    -0.75
    por
    -0.74
    monary
    -0.74
    aneous
    -0.73
    orius
    -0.71
    oding
    -0.70
    ascript
    -0.70
    ridges
    -0.69
    phrine
    -0.68
    POSITIVE LOGITS
    ship
    0.77
    geist
    0.73
    TextColor
    0.66
    Write
    0.65
    vance
    0.64
    bye
    0.62
    ingly
    0.61
     Rid
    0.61
    ependence
    0.60
    Picture
    0.60
    Activations Density 0.149%

    No Known Activations