© 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. 22505
    Prev
    Next
    INDEX
    Explanations

    links or references to videos

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts related to navigating media content, especially videos

    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
    代
    -0.69
    olicited
    -0.66
    minecraft
    -0.64
    plant
    -0.61
    dp
    -0.58
    restrial
    -0.58
    Pod
    -0.56
    soever
    -0.55
    kj
    -0.55
     communicated
    -0.54
    POSITIVE LOGITS
     Expand
    0.89
     enlarge
    0.82
     gallery
    0.82
     thumbnail
    0.76
     enlarg
    0.74
     scrolling
    0.73
    larg
    0.72
     BELOW
    0.71
    below
    0.68
     scroll
    0.68
    Activations Density 0.090%

    No Known Activations