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

    Neuronpedia

    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. 1-RES-JB
    11. 11620
    Prev
    Next
    INDEX
    Explanations

    fragments or terms related to fragmentation, breaking apart, or splitting

    oai_token-act-pair · gpt-3.5-turbo

    references to fragmented objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    perature
    -0.75
    Keefe
    -0.74
    rouse
    -0.71
    perm
    -0.70
    sburgh
    -0.68
    sky
    -0.68
    orney
    -0.66
    OPA
    -0.66
    Demand
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
     fragments
    1.40
     fragment
    1.25
     Frag
    1.15
     fragmentation
    1.06
     fragmented
    1.00
    Frag
    0.96
     shards
    0.89
     Shards
    0.79
    glass
    0.79
    mentation
    0.78
    Activations Density 0.010%

    No Known Activations