© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    historical events and political occurrences

    oai_token-act-pair · gpt-3.5-turbo

    key historical events and significant figures

    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
    */(
    -0.77
    Dialogue
    -0.68
    é¾įåĸļ士
    -0.67
    )))
    -0.65
    )].
    -0.65
    ĵĺ
    -0.64
    ))))
    -0.64
    ]."
    -0.63
    CHAT
    -0.63
     please
    -0.62
    POSITIVE LOGITS
     1964
    0.69
     1861
    0.67
     nineteen
    0.65
     overth
    0.64
    oslov
    0.63
     Soviet
    0.63
     pioneer
    0.62
     postwar
    0.61
    kefeller
    0.61
     1932
    0.60
    Activations Density 2.057%

    No Known Activations