© 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
    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. 15103
    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
    veland
    -0.77
    abwe
    -0.76
    plin
    -0.75
    edIn
    -0.71
     bombard
    -0.68
    isks
    -0.67
    EStream
    -0.64
    abit
    -0.64
     Morrow
    -0.64
    arov
    -0.63
    POSITIVE LOGITS
    ortment
    0.75
    said
    0.74
    suit
    0.66
    MAT
    0.66
    è£
    0.62
    thumbnails
    0.62
     SECTION
    0.61
     antioxid
    0.61
    Tonight
    0.60
    orned
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.