© 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. 4-RES-JB
    11. 17038
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Bravo television series and associated personalities

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

    No Comments

    Negative Logits
    folk
    -0.89
    istors
    -0.85
    vertisements
    -0.85
    omon
    -0.85
    etary
    -0.85
    stall
    -0.80
    izations
    -0.79
    papers
    -0.79
    istic
    -0.79
    tops
    -0.79
    POSITIVE LOGITS
    xual
    0.89
     Bravo
    0.88
     Bunny
    0.80
    vec
    0.80
    VO
    0.79
    ILLE
    0.77
    INO
    0.74
    BIL
    0.71
    âĺħâĺħ
    0.70
     Kafka
    0.69
    Activations Density 0.042%

    No Known Activations