© 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. 3-RES-JB
    11. 11926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gettable
    -0.77
    gotten
    -0.73
     ts
    -0.73
    ealous
    -0.68
    today
    -0.68
     forwarded
    -0.68
     warr
    -0.67
    ulsive
    -0.66
    ish
    -0.66
     looph
    -0.64
    POSITIVE LOGITS
    DVD
    0.74
    ãĤ©
    0.72
    çīĪ
    0.71
    Vert
    0.70
    ãĥīãĥ©ãĤ´ãĥ³
    0.67
     moniker
    0.67
     Brotherhood
    0.67
     ISS
    0.67
    æµ
    0.66
    LAB
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.