© 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. 5919
    Prev
    Next
    INDEX
    Explanations

    words related to political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ign."

    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
     Springfield
    -0.74
    bian
    -0.72
    HAHAHAHA
    -0.70
     Spears
    -0.65
    ------------------------------------------------
    -0.65
    successfully
    -0.62
    ---------------
    -0.61
    ----------------
    -0.60
     STATS
    -0.59
     Span
    -0.59
    POSITIVE LOGITS
    ments
    1.12
    ificant
    1.08
    antly
    0.99
    atories
    0.97
    mentation
    0.96
    eous
    0.95
    atures
    0.93
    iew
    0.93
    itory
    0.93
    ame
    0.90
    Activations Density 0.010%

    No Known Activations