© 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 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. 9-RES-JB
    11. 19439
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and other connective phrases that indicate relations or comparisons

    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
    icc
    -0.71
    iji
    -0.70
    ct
    -0.68
    qt
    -0.67
     crate
    -0.65
    enium
    -0.63
    eks
    -0.62
    agar
    -0.60
    Invalid
    -0.59
    iste
    -0.59
    POSITIVE LOGITS
     secondly
    1.04
     finally
    1.00
     furthermore
    0.99
    theless
    0.92
     alternatively
    0.82
     consequently
    0.76
     moreover
    0.76
     thence
    0.76
     ACTIONS
    0.71
     importantly
    0.71
    Activations Density 0.089%

    No Known Activations