© 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. 11387
    Prev
    Next
    INDEX
    Explanations

    security-related information related to organizations and identities, specifically focusing on ensuring the return of data

    oai_token-act-pair · gpt-3.5-turbo

    entities related to organizations and qualifications in formal 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
    ²¾
    -0.83
    DOC
    -0.66
    20439
    -0.62
    akov
    -0.61
    iencies
    -0.59
     bumper
    -0.59
    inctions
    -0.59
     Proper
    -0.59
    udden
    -0.59
    enko
    -0.58
    POSITIVE LOGITS
    LP
    0.72
    actionDate
    0.61
     1889
    0.61
     Osw
    0.60
     Tul
    0.59
    ItemThumbnailImage
    0.57
    razil
    0.57
    JV
    0.56
     840
    0.56
    mopolitan
    0.55
    Activations Density 0.345%

    No Known Activations