© 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. 4116
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Phillips."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Phillips."

    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
    ctors
    -0.80
    ERAL
    -0.78
    gary
    -0.74
    clud
    -0.72
     quo
    -0.72
    hibition
    -0.71
    fy
    -0.70
    Interstitial
    -0.67
    ered
    -0.67
    think
    -0.66
    POSITIVE LOGITS
    ippi
    1.05
     Lovecraft
    0.91
    ussen
    0.89
     Parsons
    0.75
    sey
    0.74
    pie
    0.74
    atile
    0.70
    hift
    0.69
    ions
    0.69
    iffe
    0.68
    Activations Density 0.024%

    No Known Activations