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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19113
    Prev
    Next
    INDEX
    Explanations

    references to rankings or numerical positions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    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
     lag
    -0.64
    etheless
    -0.60
    staking
    -0.60
    ãĥ¼ãĥĨ
    -0.59
     confidentiality
    -0.55
     luc
    -0.54
     disturbed
    -0.54
     enthus
    -0.54
     pear
    -0.54
     herds
    -0.52
    POSITIVE LOGITS
     1
    0.91
     2
    0.84
    1
    0.81
     3
    0.80
     8
    0.77
     4
    0.76
     7
    0.76
     6
    0.75
     22
    0.75
     5
    0.73
    Activations Density 0.024%

    No Known Activations