© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23580
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    comparative statistics and data regarding percentages and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.59
     corners
    -0.59
    èª
    -0.59
    ¬¼
    -0.57
     POW
    -0.57
    LG
    -0.56
    andals
    -0.55
    tips
    -0.55
    WIND
    -0.54
     forks
    -0.54
    POSITIVE LOGITS
     36
    0.84
     37
    0.84
     12
    0.83
     33
    0.82
     32
    0.82
     38
    0.80
     42
    0.79
     39
    0.79
     31
    0.76
     48
    0.75
    Activations Density 0.601%

    No Known Activations