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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 7267
    Prev
    Next
    INDEX
    Explanations

    short phrases mentioning groups or individuals and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and expressions of addition or connection in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "],
    -0.72
    WORK
    -0.68
    blogspot
    -0.63
    hart
    -0.61
    itiz
    -0.59
    ])
    -0.59
    Times
    -0.58
    Alert
    -0.58
    vec
    -0.57
    iuses
    -0.57
    POSITIVE LOGITS
     indeed
    1.40
     consequently
    1.33
     therefore
    1.32
     hence
    1.25
     furthermore
    1.25
     preferably
    1.23
     especially
    1.20
     moreover
    1.18
     thus
    1.14
     possibly
    1.13
    Activations Density 0.180%

    No Known Activations