© 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. 10-RES-JB
    11. 756
    Prev
    Next
    INDEX
    Explanations

    words related to decisions or choices with an emphasis on consequences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to value and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.85
    ãĥīãĥ©
    -0.83
    azines
    -0.79
    Sources
    -0.79
    ideos
    -0.78
    orks
    -0.78
    ombies
    -0.77
    mes
    -0.75
    paces
    -0.74
    urations
    -0.74
    POSITIVE LOGITS
     worth
    1.03
     unto
    1.02
     breaker
    1.02
     worthy
    0.97
    brainer
    0.94
     borne
    0.94
     impossibility
    0.92
     reminder
    0.91
    breaker
    0.87
    less
    0.84
    Activations Density 0.283%

    No Known Activations