© 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. 6-RES-JB
    11. 2692
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a conditional relationship

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating hypothetical situations or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enos
    -0.74
    FIELD
    -0.73
    76561
    -0.71
    Interest
    -0.70
    ipple
    -0.68
    atana
    -0.66
     dishes
    -0.64
    rative
    -0.63
    ogly
    -0.63
    ouk
    -0.63
    POSITIVE LOGITS
     Polly
    0.82
     existed
    0.73
     wiser
    0.72
     hindsight
    0.68
     Bett
    0.67
     Gad
    0.64
     âĢİ
    0.64
     Kinn
    0.64
     Ago
    0.63
     sooner
    0.62
    Activations Density 0.508%

    No Known Activations