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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 9004
    Prev
    Next
    INDEX
    Explanations

    mentions of biotechnology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biology and biotechnology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tongue
    -0.72
     Jagu
    -0.69
    ĸļ
    -0.63
    claw
    -0.60
     Span
    -0.59
     Devils
    -0.59
     Dominican
    -0.58
     Cheong
    -0.57
     Isle
    -0.55
     Khe
    -0.55
    POSITIVE LOGITS
    rical
    1.03
    osate
    1.03
    eor
    0.99
    ilic
    0.98
    ics
    0.84
    ufact
    0.83
    ternity
    0.83
    anical
    0.82
    vernment
    0.80
    rencies
    0.79
    Activations Density 0.105%

    No Known Activations