© 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. 0-RES-JB
    11. 17927
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "acco"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Tobacco" from "Rocket Raccoon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bound
    -0.70
     Kath
    -0.63
     spell
    -0.62
     Ally
    -0.61
     MN
    -0.61
     Gw
    -0.61
     shaking
    -0.59
     Lands
    -0.59
     Merlin
    -0.59
     ge
    -0.58
    POSITIVE LOGITS
    acco
    5.12
    acca
    1.29
    atto
    1.23
    arette
    1.21
    apers
    1.11
    aco
    1.11
     Tobacco
    1.08
    abwe
    1.05
    atos
    1.05
    cig
    1.03
    Activations Density 0.013%

    No Known Activations