© 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. 1737
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of letters, including characters, writing, and communication

    oai_token-act-pair · gpt-3.5-turbo

    references to letters and letter combinations in various contexts

    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
    rolet
    -0.85
    roxy
    -0.78
    gpu
    -0.74
    orsi
    -0.74
    ivals
    -0.72
    tg
    -0.72
    ESCO
    -0.69
    rises
    -0.67
    lace
    -0.67
    eger
    -0.67
    POSITIVE LOGITS
     alphabet
    0.95
    sworth
    0.92
    forms
    0.90
     letters
    0.89
    mith
    0.85
    letter
    0.84
    press
    0.83
     abbre
    0.80
     acronym
    0.80
     spelling
    0.79
    Activations Density 0.028%

    No Known Activations