© 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. 10-RES-JB
    11. 20404
    Prev
    Next
    INDEX
    Explanations

    dates in DD/MM/YYYY format

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
     recall
    -0.75
     withd
    -0.74
     drinkers
    -0.72
     hunted
    -0.71
     deliveries
    -0.71
     dared
    -0.70
     chained
    -0.69
     sensitive
    -0.69
     padd
    -0.69
     hoped
    -0.68
    POSITIVE LOGITS
     [+
    1.50
    0
    1.31
    5
    1.28
    00
    1.27
    06
    1.25
    jpg
    1.24
    05
    1.23
    09
    1.21
    07
    1.19
    08
    1.17
    Activations Density 0.077%

    No Known Activations