© 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. 7-RES-JB
    11. 16765
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions that emphasize priority or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing priority or hierarchical importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.77
    ingen
    -0.73
    risome
    -0.71
    ynt
    -0.70
    arine
    -0.65
    interrupted
    -0.64
    abled
    -0.63
    zos
    -0.62
    thirst
    -0.61
    intosh
    -0.61
    POSITIVE LOGITS
     foremost
    1.01
    imester
    0.74
    ttle
    0.69
     elig
    0.67
    endment
    0.63
     Misty
    0.63
     hurdle
    0.62
    fter
    0.59
    enium
    0.59
     knockout
    0.58
    Activations Density 0.116%

    No Known Activations