© 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. 671
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or topics, such as Gothic cathedrals, nuclear weapons, or streaming services

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or significant structures, events, and entities

    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
    .).
    -0.84
    ]."
    -0.77
    .''
    -0.70
    ''.
    -0.69
    !".
    -0.66
    .�
    -0.66
    )."
    -0.65
    Engineers
    -0.63
    !).
    -0.63
    )...
    -0.61
    POSITIVE LOGITS
     rul
    0.70
    ebted
    0.67
    ':
    0.63
    undrum
    0.61
     condem
    0.60
    eport
    0.58
    ahime
    0.56
    ificant
    0.54
     scanner
    0.54
    escription
    0.54
    Activations Density 2.373%

    No Known Activations