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. 0-RES-JB
    6. 11173
    Prev
    Next
    INDEX
    Explanations

    words related to topics or references with 'ica' or 'apestica'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the suffix "ica" which may refer to various scientific, geographical, and cultural concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clamp
    -0.67
     thrust
    -0.61
     uncom
    -0.61
     uncond
    -0.60
     under
    -0.60
     Lieutenant
    -0.59
    unders
    -0.57
     largeDownload
    -0.57
     tick
    -0.57
     downward
    -0.56
    POSITIVE LOGITS
    ica
    4.54
    icas
    2.62
    ICA
    2.47
    ican
    2.08
    icans
    2.00
    ico
    1.79
    icus
    1.68
    ika
    1.65
    ique
    1.61
    icum
    1.54
    Activations Density 0.007%

    No Known Activations