© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15224
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Att" with different numerical intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to attachment or connections

    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
    assetsadobe
    -0.87
    theless
    -0.85
    enegger
    -0.79
    FTWARE
    -0.79
    ORGE
    -0.77
    ktop
    -0.76
    76561
    -0.75
     Giuliani
    -0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    ĸļ
    -0.71
    POSITIVE LOGITS
    itudes
    1.24
    ributed
    1.20
    anooga
    1.17
    itude
    1.16
    achment
    1.15
    ribute
    1.15
    ainment
    1.14
    ributes
    1.14
    ention
    1.12
    ension
    1.08
    Activations Density 0.011%

    No Known Activations