© 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. 0-RES-JB
    11. 4219
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people's names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and objects related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oral
    -0.82
    airs
    -0.80
    hole
    -0.80
    yrus
    -0.73
    holes
    -0.72
    arations
    -0.71
    iral
    -0.70
    armac
    -0.69
    activate
    -0.68
    avia
    -0.68
    POSITIVE LOGITS
     Rudd
    2.14
     Wand
    1.65
     wand
    1.61
     puck
    1.40
     tamp
    1.22
     Ord
    1.18
    suff
    1.10
     mild
    1.09
     Suff
    1.08
     Bild
    1.05
    Activations Density 0.052%

    No Known Activations