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. 6-RES-JB
    6. 24178
    Prev
    Next
    INDEX
    Explanations

    personal pronouns or pronouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to subjects and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odor
    -0.63
     Seah
    -0.63
     Oral
    -0.63
    advertisement
    -0.61
     Houses
    -0.61
     Tomorrow
    -0.60
    verting
    -0.60
     Amen
    -0.59
     Yesterday
    -0.58
     Balls
    -0.58
    POSITIVE LOGITS
    'll
    0.96
    've
    0.90
    'd
    0.86
     forg
    0.77
     learnt
    0.76
     streng
    0.75
     wont
    0.75
    sych
    0.74
    lder
    0.74
    izen
    0.73
    Activations Density 0.221%

    No Known Activations