© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21534
    Prev
    Next
    INDEX
    Explanations

    the word "panel"

    oai_token-act-pair · gpt-3.5-turbo

    references to discussion panels

    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
     CARD
    -0.63
    lihood
    -0.63
     Madison
    -0.63
    hovah
    -0.62
     Pip
    -0.61
     Pyro
    -0.61
     fundament
    -0.61
     Dame
    -0.60
     Verb
    -0.59
     Abbey
    -0.57
    POSITIVE LOGITS
    ists
    1.39
    ist
    1.17
    igans
    1.12
    isted
    0.96
    iser
    0.95
    isting
    0.89
    igan
    0.87
    lain
    0.87
    icles
    0.86
     discussion
    0.84
    Activations Density 0.024%

    No Known Activations