© 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. 11-RES-JB
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    words related to sinking or failure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sinking or submerging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uin
    -0.71
    ioch
    -0.67
    reads
    -0.63
     Unified
    -0.62
     appl
    -0.59
    beit
    -0.59
    BOOK
    -0.58
    roma
    -0.58
    grain
    -0.56
     Mechdragon
    -0.56
    POSITIVE LOGITS
     deeper
    1.01
     sunk
    0.91
     into
    0.85
     dives
    0.84
     Dive
    0.82
    hole
    0.80
    holes
    0.78
    shit
    0.78
     beneath
    0.78
     deep
    0.77
    Activations Density 0.085%

    No Known Activations