© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning different modes

    oai_token-act-pair · gpt-3.5-turbo

    different operational modes related to a system or software

    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
    enegger
    -0.85
    mony
    -0.79
    owan
    -0.76
    roma
    -0.72
    areth
    -0.72
    bley
    -0.72
    rophe
    -0.71
    istani
    -0.71
    estern
    -0.70
    ertodd
    -0.70
    POSITIVE LOGITS
    etting
    0.78
     Shift
    0.75
     upgr
    0.73
     mode
    0.67
     selector
    0.66
    quit
    0.66
     parity
    0.65
    ounce
    0.64
    skirts
    0.62
     enabled
    0.62
    Activations Density 0.033%

    No Known Activations