© 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. 7110
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication, specifically the act of telling or informing someone about something

    oai_token-act-pair · gpt-3.5-turbo
    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
    adesh
    -0.82
    imposed
    -0.73
    activity
    -0.71
     sidx
    -0.70
    everal
    -0.69
    berus
    -0.69
    served
    -0.69
    conservancy
    -0.67
    cells
    -0.66
    aband
    -0.65
    POSITIVE LOGITS
    tale
    1.43
     lies
    1.12
     stories
    1.09
    ingly
    1.08
     jokes
    1.04
     tales
    1.03
     us
    1.02
     Tale
    0.89
     tale
    0.88
     Lies
    0.87
    Activations Density 0.050%

    No Known Activations