© 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. 23814
    Prev
    Next
    INDEX
    Explanations

    mentions of engineers in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of professionals and their roles

    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
     Territories
    -0.83
    SPONSORED
    -0.60
    States
    -0.60
    AAAAAAAA
    -0.60
     DOJ
    -0.58
     Amendments
    -0.57
     VIDEOS
    -0.57
    âĶĢâĶĢâĶĢâĶĢ
    -0.57
     Pradesh
    -0.56
     annexation
    -0.56
    POSITIVE LOGITS
    paces
    1.36
    hip
    1.26
    mith
    1.16
    hips
    1.13
    pace
    1.04
    ervatives
    1.01
    folk
    0.99
     who
    0.97
    ervative
    0.88
    '
    0.87
    Activations Density 0.242%

    No Known Activations