© 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 EvalsExportsinterp-engineNEWAPI 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. 1100
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific groups of people or positions, such as "representative," "program managers," "nudists," "middle-class Americans," and "writer advocates."

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people and their characteristics

    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
    Fla
    -0.82
    Tenn
    -0.75
    Jess
    -0.73
     Tropical
    -0.73
    Ore
    -0.72
    Nev
    -0.70
    Planet
    -0.69
    onet
    -0.66
    Ga
    -0.65
    Closure
    -0.65
    POSITIVE LOGITS
     are
    1.41
     aren
    1.27
     behave
    1.23
     tend
    1.22
     themselves
    1.20
     were
    1.19
     cannot
    1.16
     behaved
    1.12
     excel
    1.11
     prefer
    1.11
    Activations Density 0.436%

    No Known Activations