© 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. 10-RES-JB
    11. 21336
    Prev
    Next
    INDEX
    Explanations

    phrases referring to general topics or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance or centrality of a concept in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geons
    -0.74
    inth
    -0.65
    bal
    -0.64
    nai
    -0.62
    lift
    -0.61
    ridor
    -0.60
    estamp
    -0.60
    mes
    -0.59
    racuse
    -0.59
     guiIcon
    -0.59
    POSITIVE LOGITS
    uding
    1.04
    uring
    0.99
    usion
    0.93
     downhill
    0.91
    ocating
    0.85
    ergic
    0.84
     ABOUT
    0.79
     encomp
    0.78
     conjecture
    0.78
    edged
    0.76
    Activations Density 0.045%

    No Known Activations