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. 8-RES-JB
    6. 14651
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ch'

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phonetic sound "ch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.69
     redes
    -0.69
    ERC
    -0.68
     corrid
    -0.67
    PDATE
    -0.66
    GMT
    -0.65
     Soy
    -0.64
    TEXTURE
    -0.63
    DEN
    -0.61
    ACTION
    -0.61
    POSITIVE LOGITS
    icago
    1.25
    ambers
    1.20
    ampions
    1.17
    ampion
    1.14
    inese
    1.10
    ronic
    1.04
    ocolate
    1.04
    amps
    1.03
    icken
    1.03
    amber
    1.03
    Activations Density 0.043%

    No Known Activations