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. 10-RES-JB
    6. 24193
    Prev
    Next
    INDEX
    Explanations

    words related to names or titles ending in 'uch'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive instances of the substring "uch"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminishing
    -0.66
     discontin
    -0.66
    ework
    -0.65
     unrestricted
    -0.58
     futures
    -0.56
    END
    -0.55
    GMT
    -0.55
    govtrack
    -0.55
     Amos
    -0.54
     tampering
    -0.54
    POSITIVE LOGITS
    icago
    1.29
    anan
    1.17
    arist
    1.09
    arest
    1.04
    ar
    0.90
    ars
    0.83
    itect
    0.83
    ynski
    0.81
    atin
    0.81
    avez
    0.81
    Activations Density 0.016%

    No Known Activations