© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iannopoulos
    -0.70
    Tube
    -0.62
     vomiting
    -0.58
     vein
    -0.58
     Syndrome
    -0.57
     fumes
    -0.57
    rily
    -0.56
     syndrome
    -0.56
     borderline
    -0.55
    enberg
    -0.54
    POSITIVE LOGITS
    ĸļ
    1.29
    ©¶æ¥µ
    0.92
    ģĸ
    0.77
    arty
    0.77
    actionDate
    0.75
    }\
    0.74
    HUD
    0.74
    ihu
    0.73
    iture
    0.73
    phabet
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.