Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16892
    Prev
    Next
    INDEX
    Explanations

    terms related to significant problems or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges and difficulties faced by society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.77
    ossip
    -0.75
     vomit
    -0.73
     curls
    -0.70
    ensional
    -0.70
    Rules
    -0.69
    vez
    -0.68
    Bonus
    -0.66
    tein
    -0.66
    morph
    -0.65
    POSITIVE LOGITS
     facing
    1.43
     confronting
    1.31
     faced
    1.24
     posed
    1.11
     plag
    1.05
     humankind
    0.94
     looming
    0.93
     confronted
    0.91
     ahead
    0.91
     confronts
    0.90
    Activations Density 0.222%

    No Known Activations