© 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. 17492
    Prev
    Next
    INDEX
    Explanations

    paired words/phrases with a special character 'Ċ' separating them, potentially related to lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of significant announcements or resolutions

    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
     dime
    -0.86
     Shelby
    -0.77
     honors
    -0.75
     Rutherford
    -0.75
     Vaughn
    -0.73
     Floyd
    -0.70
    phia
    -0.70
    boro
    -0.70
     spiders
    -0.68
     treasure
    -0.68
    POSITIVE LOGITS
    ccording
    1.12
    Translation
    1.10
    However
    1.09
    Meanwhile
    1.05
    Around
    1.04
    According
    1.03
    Official
    1.02
    Refer
    1.01
    Pakistan
    1.01
    Moreover
    0.99
    Activations Density 0.538%

    No Known Activations