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

    Neuronpedia

    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. 18625
    Prev
    Next
    INDEX
    Explanations

    Keywords related to the impact, observation, or perception of events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to impactful events, issues, or policies related to societal problems

    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
    angan
    -0.62
    ranged
    -0.60
    aves
    -0.59
    dit
    -0.59
    anke
    -0.56
     guesses
    -0.56
    host
    -0.56
     Franks
    -0.56
     Reserv
    -0.55
     Subject
    -0.55
    POSITIVE LOGITS
     unfold
    1.49
     firsthand
    1.36
     happen
    1.20
     emerge
    1.20
     happening
    1.08
     unfolding
    1.04
     crumble
    1.02
     occur
    1.01
     evolve
    1.00
     differently
    0.99
    Activations Density 0.388%

    No Known Activations