© 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. 9-RES-JB
    11. 19509
    Prev
    Next
    INDEX
    Explanations

    terms related to issues or concepts requiring deep thought and understanding, such as evolutionary biology, justice, dominance, linguistics, citizenship, time, ignorance, and hypocrisy

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to justice and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.80
    eneg
    -0.70
    MpServer
    -0.66
    arnaev
    -0.66
    abella
    -0.65
    ħĭ
    -0.65
    arthed
    -0.63
    SpaceEngineers
    -0.63
    otte
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
    POSITIVE LOGITS
     wherein
    0.91
     whereby
    0.86
    !.
    0.84
    .
    0.82
    !
    0.81
     compounded
    0.76
     perpetrated
    0.75
     coupled
    0.74
     sandwic
    0.74
    !:
    0.73
    Activations Density 0.338%

    No Known Activations