© 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. 13471
    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
    lux
    -0.78
    leck
    -0.70
    ative
    -0.69
    izons
    -0.67
    hab
    -0.67
    ateral
    -0.67
    devices
    -0.66
    cyclop
    -0.65
    part
    -0.64
    acet
    -0.63
    POSITIVE LOGITS
     corrid
    0.84
    é¾
    0.75
    roth
    0.74
    catentry
    0.73
     showc
    0.70
    ãĥĥãĥī
    0.68
     derby
    0.68
     DRAG
    0.67
    CRIP
    0.62
     challeng
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.