© 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. 1-RES-JB
    11. 8564
    Prev
    Next
    INDEX
    Explanations

    organizations or individuals associated with formal letters or communications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "letter"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsi
    -0.75
    rolet
    -0.72
    afort
    -0.66
    VK
    -0.66
    minster
    -0.66
    amera
    -0.63
    BLIC
    -0.62
    alsh
    -0.62
    ategory
    -0.62
    RELATED
    -0.61
    POSITIVE LOGITS
     letter
    1.08
     letters
    0.99
    Letter
    0.99
    letter
    0.93
    worms
    0.90
    worm
    0.89
    boxing
    0.84
     Cipher
    0.81
    velop
    0.81
     penned
    0.81
    Activations Density 0.014%

    No Known Activations