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. 175
    Prev
    Next
    INDEX
    Explanations

    information or commands specifically addressed to the reader, such as instructions or personalized notifications

    oai_token-act-pair · gpt-3.5-turbo

    references to the second-person possessive pronoun "Your."

    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
    ORGE
    -0.60
     wage
    -0.56
    lier
    -0.56
    â̲
    -0.55
     riot
    -0.55
    ijk
    -0.54
     grav
    -0.53
    inement
    -0.53
     figure
    -0.53
     few
    -0.52
    POSITIVE LOGITS
     Your
    3.19
    Your
    2.54
    your
    2.20
     YOUR
    2.14
     Yourself
    2.02
     your
    1.75
     You
    1.64
     yours
    1.58
     Our
    1.49
     yourselves
    1.37
    Activations Density 0.014%

    No Known Activations