© 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. 2-RES-JB
    11. 9014
    Prev
    Next
    INDEX
    Explanations

    historical or traditional contexts or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to historical and traditional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    him
    -0.89
    ity
    -0.85
    ysis
    -0.82
    tein
    -0.78
    plan
    -0.76
    er
    -0.73
     Breach
    -0.71
    ters
    -0.71
     Coverage
    -0.70
    ion
    -0.70
    POSITIVE LOGITS
     housed
    0.95
     exting
    0.86
     wielded
    0.85
     relied
    0.84
     traditionally
    0.84
    ©¶æ
    0.83
     oppressed
    0.83
     conduc
    0.82
     overlooked
    0.81
     marketed
    0.81
    Activations Density 0.007%

    No Known Activations