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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12096
    Prev
    Next
    INDEX
    Explanations

    instances where the pronoun "it" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "it" and related concepts

    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
     persuade
    -0.71
     Assist
    -0.70
     persuasion
    -0.68
     accompany
    -0.66
     direct
    -0.64
    igate
    -0.63
     praising
    -0.63
    cknow
    -0.62
     urge
    -0.62
     Include
    -0.62
    POSITIVE LOGITS
     deteriorated
    1.41
     underwent
    1.37
     hasn
    1.32
     survived
    1.21
     remained
    1.20
     disappeared
    1.17
     existed
    1.16
     faded
    1.15
     survives
    1.15
     wasn
    1.14
    Activations Density 0.421%

    No Known Activations