Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4723
    Prev
    Next
    INDEX
    Explanations

    references to technical terms or specifications, such as levels, containment protocols, or geometrical and archaeological terms

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to types of sites, offenses, or classifications

    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
    untled
    -0.78
     omission
    -0.67
    umsy
    -0.63
    ifix
    -0.63
    à¨
    -0.62
    theless
    -0.60
     Peb
    -0.60
    Minecraft
    -0.58
     Gutierrez
    -0.58
    staking
    -0.57
    POSITIVE LOGITS
     guiActiveUnfocused
    0.79
     (>
    0.64
    whe
    0.62
     (/
    0.62
     =>
    0.60
     (.
    0.60
     (<
    0.57
    XP
    0.56
    incial
    0.56
    fighter
    0.56
    Activations Density 0.632%

    No Known Activations