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. 9-RES-JB
    6. 6218
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs indicating actions the pronoun is taking

    oai_token-act-pair · gpt-3.5-turbo

    first-person and second-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ious
    -0.69
    liest
    -0.66
    angering
    -0.65
    inery
    -0.65
    natal
    -0.64
    lihood
    -0.63
    agement
    -0.61
     Archdemon
    -0.60
    imon
    -0.60
    scription
    -0.59
    POSITIVE LOGITS
     goes
    0.79
     go
    0.75
    eps
    0.74
     again
    0.67
     sits
    0.64
    comes
    0.64
     stands
    0.63
     belong
    0.63
    go
    0.62
     went
    0.62
    Activations Density 0.072%

    No Known Activations