© 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. 9367
    Prev
    Next
    INDEX
    Explanations

    the year 1973

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1973 and its significance in various contexts

    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
    tro
    -0.80
    ventus
    -0.76
    robe
    -0.76
     entirety
    -0.75
    ked
    -0.71
    Edge
    -0.70
    cho
    -0.69
    plan
    -0.68
    opher
    -0.68
    king
    -0.67
    POSITIVE LOGITS
    ĸļ
    1.06
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.97
     1973
    0.89
    1968
    0.86
     1972
    0.85
    1971
    0.85
     1974
    0.84
     1977
    0.83
     ILCS
    0.82
    1966
    0.81
    Activations Density 0.016%

    No Known Activations