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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 23908
    Prev
    Next
    INDEX
    Explanations

    technical and detailed language used in documents or articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to effectiveness or performance of actions and processes

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

    No Comments

    Negative Logits
     Originally
    -0.50
     Reconstruction
    -0.49
    Drag
    -0.48
     Transparency
    -0.48
     Fract
    -0.46
     Latest
    -0.46
     Drag
    -0.45
     nutshell
    -0.45
     Torrent
    -0.45
     Collider
    -0.44
    POSITIVE LOGITS
    '."
    0.81
    .).
    0.75
    ]."
    0.75
    !".
    0.72
    atever
    0.70
     anyway
    0.70
    ).[
    0.69
    .'"
    0.67
    )."
    0.67
    '.
    0.67
    Activations Density 3.917%

    No Known Activations