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. 0-RES-JB
    6. 11059
    Prev
    Next
    INDEX
    Explanations

    business-related keywords or terms

    oai_token-act-pair · gpt-3.5-turbo

    components related to statistics and chat functionalities

    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
    arten
    -0.72
     foremost
    -0.65
     ·
    -0.64
     abiding
    -0.63
     revolving
    -0.62
     pressing
    -0.62
     obstacles
    -0.61
     leading
    -0.60
     snail
    -0.60
     opacity
    -0.58
    POSITIVE LOGITS
    Stats
    3.30
    stats
    1.73
    Brew
    1.13
    wcs
    0.91
    acus
    0.87
    Info
    0.84
    Chat
    0.83
    Stat
    0.83
    TPP
    0.81
    Meta
    0.81
    Activations Density 0.015%

    No Known Activations