© 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. 7-RES-JB
    11. 21803
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory and safety actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    facing
    -0.70
    nikov
    -0.70
     Joker
    -0.59
    aples
    -0.57
     Ghostbusters
    -0.56
    lda
    -0.56
    essing
    -0.56
    opped
    -0.55
     Sands
    -0.55
     mound
    -0.55
    POSITIVE LOGITS
    ICA
    0.80
    ITION
    0.75
    exempt
    0.73
    senal
    0.71
     acronym
    0.70
    LET
    0.70
    lishes
    0.69
    soDeliveryDate
    0.68
     disbanded
    0.68
    ENE
    0.67
    Activations Density 0.566%

    No Known Activations