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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 17773
    Prev
    Next
    INDEX
    Explanations

    years in the 1960s

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verbally
    -0.67
     voic
    -0.62
     spontaneously
    -0.57
    Tickets
    -0.56
     continu
    -0.56
     deserving
    -0.55
    wat
    -0.55
     vows
    -0.54
     witty
    -0.54
    EStreamFrame
    -0.54
    POSITIVE LOGITS
    s
    1.21
    sie
    0.91
    enthal
    0.91
    ies
    0.90
    sburg
    0.90
    eenth
    0.90
    ixties
    0.90
    -'
    0.85
    eties
    0.85
    ties
    0.84
    Activations Density 0.058%

    No Known Activations