© 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. 20002
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms associated with locations or events, potentially related to history or news

    oai_token-act-pair · gpt-3.5-turbo

    references to specific Greek terms or phrases

    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
     philos
    -0.85
    erv
    -0.81
    ipeg
    -0.76
    ensical
    -0.73
     FANTASY
    -0.71
    oyer
    -0.70
     Enlightenment
    -0.68
    irtual
    -0.68
    ify
    -0.67
    oppable
    -0.66
    POSITIVE LOGITS
     duct
    0.73
     Astron
    0.67
    qs
    0.63
     Crow
    0.63
     drill
    0.63
    Quantity
    0.62
    phies
    0.60
     Ba
    0.59
     bere
    0.59
    verb
    0.59
    Activations Density 0.000%

    No Known Activations