© 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. 2-RES-JB
    11. 13049
    Prev
    Next
    INDEX
    Explanations

    dates expressed in four digits

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly from the 1960s to the 1970s

    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
    plan
    -0.77
     unw
    -0.73
    izen
    -0.73
     entirety
    -0.71
    tro
    -0.70
    unders
    -0.70
    vere
    -0.68
    ked
    -0.67
     heartbeat
    -0.67
    ams
    -0.66
    POSITIVE LOGITS
    ĸļ
    0.87
     onwards
    0.81
    1968
    0.79
    å¹
    0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
     ILCS
    0.75
     onward
    0.73
    1966
    0.71
     "$:/
    0.71
    1967
    0.70
    Activations Density 0.019%

    No Known Activations