© 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. 15160
    Prev
    Next
    INDEX
    Explanations

    complex or complicated topics or situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to complexity or complications

    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
     hungry
    -0.66
    gin
    -0.63
     thirsty
    -0.61
     sweat
    -0.61
    earchers
    -0.60
     sweaty
    -0.60
     paycheck
    -0.59
     tides
    -0.58
     alumni
    -0.58
     naked
    -0.57
    POSITIVE LOGITS
    aneous
    0.83
    terday
    0.78
     Procedure
    0.76
    tenance
    0.76
     explanations
    0.75
    lihood
    0.73
     Amendments
    0.73
    emort
    0.71
    aneously
    0.70
     solutions
    0.69
    Activations Density 0.145%

    No Known Activations