© 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. 8-RES-JB
    11. 6536
    Prev
    Next
    INDEX
    Explanations

    phrases indicating leading, guiding, or directing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.68
    TB
    -0.65
     roy
    -0.63
    sle
    -0.62
    checks
    -0.61
    RP
    -0.59
     spawned
    -0.59
     multiplier
    -0.58
    anni
    -0.58
     squeezed
    -0.58
    POSITIVE LOGITS
     believe
    0.87
     conclude
    0.85
     conclusions
    0.81
     Oliv
    0.74
     realize
    0.73
     realise
    0.73
    ãĤ©
    0.73
     pursue
    0.71
     discover
    0.71
    ixel
    0.70
    Activations Density 0.164%

    No Known Activations