© 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. 1522
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, such as cities or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to homes or residences, particularly in the context of lifestyle and mobility

    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
    ]."
    -0.69
    )."
    -0.65
     gases
    -0.59
    ?).
    -0.58
    ).[
    -0.58
    anwhile
    -0.56
    ").
    -0.56
    ]).
    -0.55
     subtract
    -0.55
     whiff
    -0.54
    POSITIVE LOGITS
     ðŁĻĤ
    0.65
     Patreon
    0.62
    nesday
    0.60
     :)
    0.60
     :-)
    0.58
     colle
    0.58
    owship
    0.57
    intend
    0.54
     Anthropology
    0.54
    minist
    0.54
    Activations Density 1.540%

    No Known Activations