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. 3-RES-JB
    6. 18910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anian
    -0.88
    amily
    -0.73
    SPONSORED
    -0.70
    ioned
    -0.70
    armed
    -0.69
     suspic
    -0.65
    cient
    -0.64
     Clause
    -0.61
    room
    -0.61
    eyed
    -0.60
    POSITIVE LOGITS
    \\\\\\\\
    0.78
    ̶
    0.69
     Canaveral
    0.67
    voy
    0.67
    Ocean
    0.66
    GY
    0.66
    NAS
    0.65
    jri
    0.65
    inar
    0.65
    ãĤ¦
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.