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. 0-RES-JB
    6. 971
    Prev
    Next
    INDEX
    Explanations

    words related to actions involving a quick movement or strong emotional response

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to "sh" or "sh" sounds across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marine
    -0.72
    arte
    -0.70
    reciation
    -0.67
    phabet
    -0.66
    OTAL
    -0.66
    fax
    -0.66
    avis
    -0.66
    alde
    -0.66
    heimer
    -0.66
    eur
    -0.66
    POSITIVE LOGITS
     sh
    3.32
     Sh
    1.80
    Sh
    1.71
    sh
    1.68
     shards
    1.49
     SH
    1.46
     shin
    1.27
    sha
    1.25
     sho
    1.24
     shack
    1.22
    Activations Density 0.008%

    No Known Activations