© 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. 10-RES-JB
    11. 11126
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a group of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "They" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.62
    hander
    -0.59
    EngineDebug
    -0.58
     Torrent
    -0.58
    INGTON
    -0.58
     Cerberus
    -0.55
     sizeof
    -0.55
     whichever
    -0.55
    Development
    -0.55
     Whe
    -0.54
    POSITIVE LOGITS
    've
    1.11
     also
    1.10
     furthermore
    1.08
    're
    1.07
     certainly
    1.04
    'll
    1.02
    gemony
    0.99
     therefore
    0.97
     deserve
    0.96
    resy
    0.95
    Activations Density 0.254%

    No Known Activations