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. 22438
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics

    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
     comr
    -0.57
     philos
    -0.57
     RTX
    -0.51
     evolved
    -0.50
    âĹ¼
    -0.50
     afore
    -0.49
     negativity
    -0.48
     predec
    -0.48
     pandemonium
    -0.47
     subsequ
    -0.47
    POSITIVE LOGITS
    6
    1.21
    8
    1.20
    9
    1.20
    5
    1.19
    4
    1.17
    0
    1.17
    3
    1.17
    7
    1.16
    1
    1.11
    2
    1.10
    Activations Density 0.079%

    No Known Activations