© 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. 6526
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating exclusivity or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or limitation

    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
    idon
    -0.77
    ducers
    -0.67
    insula
    -0.65
    phen
    -0.63
    PI
    -0.60
    hement
    -0.58
    mire
    -0.58
     Dynamics
    -0.57
    stice
    -0.57
     Cot
    -0.56
    POSITIVE LOGITS
     marginally
    1.06
     lasted
    0.99
     scratched
    0.92
     kidding
    0.86
     cared
    0.85
     allowed
    0.83
     cares
    0.79
     scratches
    0.78
     lasts
    0.77
     pretended
    0.76
    Activations Density 0.057%

    No Known Activations