© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6513
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the specific initial W followed by a single upper-case letter

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'W' in various contexts

    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
    EStream
    -0.83
     succeeding
    -0.76
    ioch
    -0.74
    displayText
    -0.70
    netflix
    -0.70
    arial
    -0.67
     Hades
    -0.67
     correcting
    -0.64
    orescent
    -0.64
    ãĥŀ
    -0.64
    POSITIVE LOGITS
    atts
    1.07
    ulf
    1.04
    ITNESS
    1.04
    ijn
    1.00
    OOD
    1.00
    ND
    1.00
    TF
    0.99
    NN
    0.98
    atson
    0.98
    rench
    0.97
    Activations Density 0.026%

    No Known Activations