© 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. 0-RES-JB
    6. 6327
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wallet
    -0.76
    ND
    -0.67
     garden
    -0.65
    addy
    -0.65
     gardening
    -0.63
     tie
    -0.62
     deed
    -0.61
     plug
    -0.60
    ã쮿
    -0.59
     digs
    -0.58
    POSITIVE LOGITS
     actionGroup
    0.90
    enary
    0.89
    milo
    0.79
    ãĥķãĤ©
    0.78
    who
    0.77
    ģĸ
    0.76
     Vall
    0.72
    amsung
    0.72
    odox
    0.70
    whe
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.