© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17628
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to a specific entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newcom
    -0.73
    £ı
    -0.68
     contrasting
    -0.62
    onde
    -0.61
    mbuds
    -0.60
     pestic
    -0.59
    IDE
    -0.59
     substrate
    -0.58
     Grimoire
    -0.58
     methodological
    -0.58
    POSITIVE LOGITS
    'll
    1.69
     ain
    1.55
     WILL
    1.34
     won
    1.31
     wont
    1.24
    's
    1.22
     sucks
    1.19
     doesn
    1.19
     hurts
    1.19
     will
    1.16
    Activations Density 0.252%

    No Known Activations