© 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. 14739
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying and solving problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to solving problems

    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
    ammy
    -0.74
    akening
    -0.74
    ardy
    -0.70
    umption
    -0.67
    akin
    -0.66
    aving
    -0.65
    anwhile
    -0.63
    icipated
    -0.62
    erker
    -0.61
    oths
    -0.61
    POSITIVE LOGITS
     solve
    1.07
    ĵĺ
    0.95
     solving
    0.95
    vable
    0.89
     solved
    0.83
     solves
    0.83
    itaire
    0.79
    æ©
    0.78
    ĸļ
    0.76
    idian
    0.74
    Activations Density 0.017%

    No Known Activations