© 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. 7506
    Prev
    Next
    INDEX
    Explanations

    numbers such as dates, percentages, and values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly relating to statistics or scores

    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
    rd
    -0.78
    aith
    -0.75
    andise
    -0.74
    reek
    -0.71
     indo
    -0.71
    ende
    -0.71
    pires
    -0.68
    akes
    -0.67
    iday
    -0.66
    ame
    -0.66
    POSITIVE LOGITS
    6666
    0.94
    20439
    0.90
    384
    0.87
    554
    0.79
    66666666
    0.79
     Decay
    0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.77
    İĭ
    0.77
    0100
    0.75
    016
    0.73
    Activations Density 0.047%

    No Known Activations