© 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. 23348
    Prev
    Next
    INDEX
    Explanations

    words related to spelling and pronunciation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spelling and its rules

    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
    DEM
    -0.85
    elaide
    -0.80
    ropri
    -0.76
    liga
    -0.75
    igious
    -0.75
    exper
    -0.73
    uterte
    -0.71
    atri
    -0.71
    ribut
    -0.70
    udeau
    -0.69
    POSITIVE LOGITS
     spelling
    1.59
     spelled
    1.40
     phon
    1.03
     pronunciation
    0.98
    matical
    0.91
     abbrevi
    0.84
     nodd
    0.82
     typo
    0.81
     spell
    0.81
     abbre
    0.80
    Activations Density 0.008%

    No Known Activations