© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    names of individuals who are involved in legal matters or newsworthy events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police officers and related legal cases

    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
     FANTASY
    -0.76
     archived
    -0.61
     denotes
    -0.56
     circular
    -0.56
     inconsistency
    -0.55
     NEWS
    -0.55
     deduction
    -0.54
     irony
    -0.53
    BOOK
    -0.53
     NETWORK
    -0.53
    POSITIVE LOGITS
    zi
    0.73
    iani
    0.69
    $.
    0.69
    zar
    0.68
    anda
    0.67
    ovich
    0.66
    anski
    0.66
    ban
    0.64
    isi
    0.64
    inski
    0.64
    Activations Density 0.569%

    No Known Activations