© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    references to correspondents or correspondence

    oai_token-act-pair · gpt-3.5-turbo

    references to correspondents in a news or journalistic context

    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
    owered
    -0.82
    params
    -0.81
    GPU
    -0.77
    multipl
    -0.76
    oppable
    -0.74
    forcing
    -0.74
    HUD
    -0.70
    animate
    -0.69
    ghazi
    -0.69
    rugged
    -0.69
    POSITIVE LOGITS
     correspondent
    0.98
     Correspond
    0.97
    hip
    0.94
    ries
    0.89
     columnist
    0.86
     newsp
    0.83
    ship
    0.80
    ingly
    0.78
     Fellow
    0.77
     writer
    0.77
    Activations Density 0.063%

    No Known Activations