© 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. 16779
    Prev
    Next
    INDEX
    Explanations

    settings and options-related words

    oai_token-act-pair · gpt-3.5-turbo

    actions related to customization and adjustment settings

    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
    ublic
    -0.77
    roots
    -0.75
    sect
    -0.70
    andre
    -0.69
    ãĥĪ
    -0.69
    ngth
    -0.68
    united
    -0.67
    00007
    -0.66
    llah
    -0.66
    illin
    -0.65
    POSITIVE LOGITS
     customize
    1.14
     customization
    1.05
     presets
    0.99
     depending
    0.95
     customized
    0.93
     toggle
    0.93
     customizable
    0.92
     buttons
    0.92
     custom
    0.92
     parameters
    0.91
    Activations Density 0.568%

    No Known Activations