Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9409
    Prev
    Next
    INDEX
    Explanations

    dates specified in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in the text

    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
     drift
    -0.76
     everyday
    -0.75
     mature
    -0.73
     intangible
    -0.73
     intelligent
    -0.72
     occupancy
    -0.69
     clin
    -0.69
     flock
    -0.69
     intensive
    -0.69
     extingu
    -0.68
    POSITIVE LOGITS
    pictured
    1.55
    PDF
    1.46
    pdf
    1.38
    see
    1.35
    emphasis
    1.30
    which
    1.29
    via
    1.28
    below
    1.26
    shown
    1.25
    albeit
    1.23
    Activations Density 0.172%

    No Known Activations