© 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. 3-RES-JB
    11. 9472
    Prev
    Next
    INDEX
    Explanations

    references to specific entities like companies or technologies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific organizations or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.82
     Jarrett
    -0.73
    ography
    -0.72
     Anfield
    -0.72
    ttes
    -0.72
     graves
    -0.70
     Germans
    -0.70
    lake
    -0.70
    ths
    -0.68
     Manor
    -0.68
    POSITIVE LOGITS
     ABS
    1.09
     unden
    1.07
    ILA
    1.06
     mathemat
    0.91
    acus
    0.90
     reluct
    0.88
     challeng
    0.88
    BIP
    0.85
    ħĭ
    0.81
    ENCY
    0.81
    Activations Density 0.016%

    No Known Activations