© 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. 3-RES-JB
    11. 5473
    Prev
    Next
    INDEX
    Explanations

    clauses with a sequential structure, particularly with actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation-related patterns, particularly commas

    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
    interstitial
    -0.70
     flagship
    -0.62
    cott
    -0.62
    ety
    -0.62
     mosqu
    -0.61
     encount
    -0.60
    herent
    -0.59
    è£ħ
    -0.58
    vre
    -0.58
    ¬¼
    -0.58
    POSITIVE LOGITS
     albeit
    1.07
     lest
    0.89
     but
    0.89
     although
    0.80
     though
    0.79
     etc
    0.77
    but
    0.76
     however
    0.75
     unless
    0.74
     whereas
    0.73
    Activations Density 1.117%

    No Known Activations