© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10661
    Prev
    Next
    INDEX
    Explanations

    words related to role-playing games

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating options or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.75
    etheless
    -0.70
    heit
    -0.69
    ãĥ¼ãĥĨ
    -0.67
     */
    -0.67
    alf
    -0.65
     ..."
    -0.64
    bender
    -0.62
    ista
    -0.60
     Beir
    -0.59
    POSITIVE LOGITS
    onduct
    0.74
    bernatorial
    0.67
    onductor
    0.65
     coron
    0.65
    phrine
    0.63
    GAME
    0.63
    iple
    0.61
    jriwal
    0.61
    vae
    0.61
     PROG
    0.60
    Activations Density 0.000%

    No Known Activations