© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7224
    Prev
    Next
    INDEX
    Explanations

    fragmentary pieces or parts

    oai_token-act-pair · gpt-3.5-turbo

    references to fragmented items or pieces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Keefe
    -0.78
    Reviewer
    -0.78
    CV
    -0.72
    perature
    -0.70
    sers
    -0.69
    sburgh
    -0.68
    Demand
    -0.64
    DIT
    -0.64
    keley
    -0.64
    perm
    -0.64
    POSITIVE LOGITS
     fragments
    1.21
     fragment
    1.17
     Frag
    1.05
     fragmented
    0.95
     ILCS
    0.92
    Frag
    0.87
    glass
    0.85
     fragmentation
    0.84
    bite
    0.83
    ãĤ©
    0.80
    Activations Density 0.009%

    No Known Activations