© 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. 1-RES-JB
    11. 9480
    Prev
    Next
    INDEX
    Explanations

    dates in the format of years

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific years, particularly 1938, 1939, and 1940

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isters
    -0.84
    por
    -0.81
    orns
    -0.78
    keys
    -0.77
    ops
    -0.76
    olar
    -0.75
    olves
    -0.74
    yx
    -0.73
    atom
    -0.72
    andering
    -0.71
    POSITIVE LOGITS
     1942
    1.18
     1941
    1.13
     1939
    1.13
     1943
    1.12
     1936
    1.09
     1937
    1.07
     1938
    1.04
     1944
    1.01
     1940
    0.97
     1935
    0.97
    Activations Density 0.010%

    No Known Activations