© 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. 12-RES-JB
    11. 4460
    Prev
    Next
    INDEX
    Explanations

    actions or events related to a complex scenario involving vehicles and individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    repetitive or emphatic phrases in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nods
    -0.68
     counting
    -0.64
     enough
    -0.63
     rooting
    -0.60
     nodding
    -0.60
     bleeding
    -0.60
     hust
    -0.59
     trouble
    -0.59
     raised
    -0.59
     rather
    -0.59
    POSITIVE LOGITS
    PIN
    0.96
    ĸļ
    0.93
    Prev
    0.87
    ternity
    0.86
    Ô
    0.84
    THIS
    0.84
    {{
    0.84
    License
    0.83
    Ep
    0.82
    Ý
    0.81
    Activations Density 0.115%

    No Known Activations