Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ach" and some related words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "ach" in various contexts

    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
     futures
    -0.68
    PDATE
    -0.63
    FACE
    -0.62
    fml
    -0.61
    drm
    -0.60
     beard
    -0.59
    LEASE
    -0.59
    ©¶æ
    -0.58
    ences
    -0.57
     stacking
    -0.57
    POSITIVE LOGITS
    annel
    1.07
    ieving
    1.05
    iev
    1.00
    akra
    0.99
    mann
    0.96
    rome
    0.95
    ieve
    0.95
    alos
    0.95
    icago
    0.92
    idon
    0.92
    Activations Density 0.028%

    No Known Activations