© 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 EvalsExportsAPI 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. 3420
    Prev
    Next
    INDEX
    Explanations

    pronouns 'it' and 'it has' used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    statements or claims related to observations and conclusions

    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
     Saying
    -0.64
     Dying
    -0.61
    Finish
    -0.58
     Infinite
    -0.58
     Way
    -0.58
     Spending
    -0.57
     WAY
    -0.57
     tossing
    -0.56
     Odyssey
    -0.56
     yelling
    -0.55
    POSITIVE LOGITS
     transpired
    1.26
     appears
    1.15
     beh
    1.15
     seems
    1.08
     emerges
    1.08
     emerged
    1.08
    iner
    0.95
     becomes
    0.94
     rains
    0.92
    unes
    0.92
    Activations Density 0.199%

    No Known Activations