© 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. 7-RES-JB
    11. 2132
    Prev
    Next
    INDEX
    Explanations

    instances of the word "type" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "type" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ivals
    -0.71
    =~=~
    -0.66
    ordial
    -0.66
    eming
    -0.61
    ellery
    -0.61
    negie
    -0.60
     disadvant
    -0.60
    emale
    -0.60
    rugged
    -0.57
     Admission
    -0.57
    POSITIVE LOGITS
     aloud
    1.06
    ahead
    0.90
    face
    0.84
     typing
    0.82
    faces
    0.78
    codes
    0.74
     alphabet
    0.73
     html
    0.72
     captcha
    0.72
     passwords
    0.72
    Activations Density 0.041%

    No Known Activations