© 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. 1-RES-JB
    6. 1585
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eeper
    -0.68
    uly
    -0.67
     pod
    -0.63
    Pg
    -0.62
     intuitive
    -0.62
     Maw
    -0.62
    igmatic
    -0.61
     cumbersome
    -0.60
    Closure
    -0.59
    bourg
    -0.58
    POSITIVE LOGITS
    romeda
    0.81
    uminati
    0.76
    ertodd
    0.72
    rolet
    0.67
    enegger
    0.67
    soDeliveryDate
    0.66
    Ranked
    0.64
    ãĥ¤
    0.63
    Interstitial
    0.63
    enei
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.