© 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. 7-RES-JB
    11. 8556
    Prev
    Next
    INDEX
    Explanations

    phrases related to shedding light on a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of illuminating or clarifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apons
    -0.73
    ocide
    -0.70
    asus
    -0.69
    utor
    -0.68
    hare
    -0.67
    ortex
    -0.67
    ocaly
    -0.67
     nomine
    -0.66
    oln
    -0.64
    ipt
    -0.63
    POSITIVE LOGITS
    enment
    1.06
    ening
    0.95
    weights
    0.93
    eners
    0.91
    nings
    0.89
    ener
    0.88
    hearted
    0.88
    lights
    0.86
    ened
    0.85
    eyes
    0.82
    Activations Density 0.019%

    No Known Activations