© 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. 1-RES-JB
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    words related to legal or official procedures or steps

    oai_token-act-pair · gpt-3.5-turbo

    references to preliminary procedures or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.79
    die
    -0.79
     Kinnikuman
    -0.77
    mes
    -0.70
    smart
    -0.70
     Commando
    -0.67
    gie
    -0.66
    add
    -0.66
    stood
    -0.65
    oise
    -0.65
    POSITIVE LOGITS
    iminary
    1.80
     preliminary
    1.18
     prelim
    0.97
     examination
    0.95
    spection
    0.95
     evaluations
    0.91
     guiActiveUn
    0.90
     examinations
    0.90
     explor
    0.87
     Prel
    0.84
    Activations Density 0.013%

    No Known Activations