© 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. 12117
    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
     seam
    -0.77
     compressor
    -0.72
    £ı
    -0.71
     Indra
    -0.69
     commissioned
    -0.68
     feasibility
    -0.66
     psy
    -0.63
     probe
    -0.63
     pH
    -0.63
     transformer
    -0.62
    POSITIVE LOGITS
    Vote
    0.87
    irements
    0.79
    ember
    0.76
    clus
    0.73
    Newsletter
    0.71
    ombat
    0.70
    ONT
    0.70
    Northern
    0.69
    IRE
    0.69
    ater
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.