© 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. 8-RES-JB
    11. 18579
    Prev
    Next
    INDEX
    Explanations

    various reasons, explanations, and theories

    oai_token-act-pair · gpt-3.5-turbo

    various explanations or theories regarding a particular subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĪ
    -0.77
    iversity
    -0.70
    iferation
    -0.69
    erity
    -0.67
    urance
    -0.67
     +++
    -0.64
     Democr
    -0.64
    paper
    -0.64
    aternity
    -0.63
    usters
    -0.62
    POSITIVE LOGITS
     interpretations
    1.00
     explanations
    0.99
     theories
    0.88
     scenarios
    0.87
     configurations
    0.86
     interpretation
    0.83
     imaginable
    0.77
     approaches
    0.76
     conver
    0.75
     factors
    0.75
    Activations Density 0.217%

    No Known Activations