© 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. 4-RES-JB
    11. 17204
    Prev
    Next
    INDEX
    Explanations

    common names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or notable figures mentioned in the text

    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
     Jagu
    -0.82
    netflix
    -0.80
    ĸļ
    -0.74
     footballer
    -0.74
     civilisation
    -0.72
    ahime
    -0.72
     labou
    -0.71
     realise
    -0.70
    worldly
    -0.70
     traveller
    -0.67
    POSITIVE LOGITS
     Wasserman
    1.01
     Pelosi
    0.97
     Biden
    0.96
    PAC
    0.93
     Berman
    0.92
     Santorum
    0.92
     McCain
    0.90
     Kimmel
    0.89
     Huckabee
    0.88
     Sanders
    0.88
    Activations Density 0.294%

    No Known Activations