© 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. 23260
    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
     Logged
    -0.68
     Turns
    -0.67
     tasting
    -0.67
     tasted
    -0.65
    ĻĤ
    -0.64
    fm
    -0.64
     largeDownload
    -0.64
     Variety
    -0.63
    generic
    -0.62
    arrell
    -0.62
    POSITIVE LOGITS
    itals
    0.77
    apes
    0.75
    ROM
    0.74
    ITAL
    0.73
    ramids
    0.71
    venge
    0.70
    arta
    0.70
    abies
    0.69
    ricanes
    0.68
    ibia
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.