© 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. 11336
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific anime-related term

    oai_token-act-pair · gpt-3.5-turbo

    references to specific movie titles or related terminology

    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
     Kurdistan
    -0.67
     Lyme
    -0.62
     neighbors
    -0.61
     Corpus
    -0.60
     Raqqa
    -0.60
     Reporting
    -0.60
     Islamabad
    -0.59
     depreciation
    -0.59
     reporting
    -0.58
     Certification
    -0.58
    POSITIVE LOGITS
    imo
    4.10
    atto
    1.85
    aye
    1.06
    imus
    1.04
    imum
    0.96
    uo
    0.91
    lio
    0.90
    aro
    0.88
    andro
    0.88
    angelo
    0.87
    Activations Density 0.027%

    No Known Activations