© 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. 3176
    Prev
    Next
    INDEX
    Explanations

    terms related to events, achievements, and conditions such as holidays, releases, best performances, and public happenings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluations and assessments of performance and condition

    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
     bells
    -0.83
     establishments
    -0.83
     tanks
    -0.80
     bosses
    -0.78
     portals
    -0.78
     classes
    -0.77
     thugs
    -0.76
     assemblies
    -0.76
     races
    -0.76
    ernels
    -0.76
    POSITIVE LOGITS
     spokeswoman
    0.70
     standpoint
    0.67
    ledged
    0.66
    perate
    0.64
    yssey
    0.64
    etermined
    0.63
    -
    0.63
     estimate
    0.62
    otal
    0.61
    filled
    0.61
    Activations Density 0.397%

    No Known Activations