© 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. 7-RES-JB
    11. 21168
    Prev
    Next
    INDEX
    Explanations

    words related to sharp or abrupt actions or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to racial identity and eyewitness accounts

    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
    agine
    -0.77
     Peninsula
    -0.72
     dear
    -0.65
    izoph
    -0.64
    asted
    -0.63
     Psychiatry
    -0.62
     thirds
    -0.60
    OTAL
    -0.59
    EGA
    -0.58
     adm
    -0.58
    POSITIVE LOGITS
    es
    2.47
    ively
    1.39
    ions
    1.21
    esville
    1.20
    ed
    1.16
    esian
    1.14
    esy
    1.10
    eson
    1.06
    engers
    1.04
    ing
    1.04
    Activations Density 0.154%

    No Known Activations