© 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. 7-RES-JB
    11. 13436
    Prev
    Next
    INDEX
    Explanations

    references to letters being sent or written

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of the word "letter", particularly in formal or official contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Races
    -0.75
    glers
    -0.74
     blink
    -0.72
    natureconservancy
    -0.71
    lap
    -0.70
    park
    -0.69
    variable
    -0.69
    hunt
    -0.69
    ource
    -0.68
    ahime
    -0.66
    POSITIVE LOGITS
    Dear
    1.12
     letter
    1.01
     correspondence
    0.99
     letters
    0.94
     dated
    0.93
     superiors
    0.88
     Letters
    0.85
     inbox
    0.84
    Letter
    0.83
     requesting
    0.82
    Activations Density 0.227%

    No Known Activations