© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    references to powerful and influential individuals, such as moguls or gurus

    oai_token-act-pair · gpt-3.5-turbo

    words associated with individuals who have substantial influence in their respective fields

    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
    ood
    -0.76
    endars
    -0.72
    alam
    -0.71
    ī
    -0.70
    ridges
    -0.70
    abet
    -0.70
    ulz
    -0.68
    elt
    -0.68
    ria
    -0.67
    °
    -0.67
    POSITIVE LOGITS
     mogul
    1.04
     guru
    0.84
     frontrunner
    0.82
    dinand
    0.75
    esses
    0.73
    coon
    0.72
     rabbi
    0.71
    tec
    0.70
     mog
    0.70
     pedd
    0.69
    Activations Density 0.015%

    No Known Activations