© 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. 8-RES-JB
    11. 1019
    Prev
    Next
    INDEX
    Explanations

    questions being posed or considerations being made

    oai_token-act-pair · gpt-3.5-turbo

    questions related to the societal implications of laws and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thrones
    -0.70
    çīĪ
    -0.70
    licts
    -0.70
    è¦ļéĨĴ
    -0.67
    lict
    -0.67
    axies
    -0.66
    IGH
    -0.65
    nsic
    -0.64
    PsyNetMessage
    -0.64
    ciating
    -0.64
    POSITIVE LOGITS
     ever
    0.94
     anymore
    0.92
     qualifies
    0.81
     adequately
    0.81
     properly
    0.80
     correctly
    0.79
     sufficiently
    0.73
    heit
    0.71
     appropriate
    0.70
     somehow
    0.69
    Activations Density 0.357%

    No Known Activations