© 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. 10-RES-JB
    11. 10690
    Prev
    Next
    INDEX
    Explanations

    large numbers representing quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics relevant to various contexts

    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
    ĸļ
    -0.62
    EStreamFrame
    -0.57
     poaching
    -0.54
     lobb
    -0.53
    EStream
    -0.53
     Period
    -0.52
     afore
    -0.52
    sole
    -0.52
     partying
    -0.52
     celebrated
    -0.51
    POSITIVE LOGITS
    36
    0.85
    38
    0.84
    66
    0.83
    39
    0.83
    41
    0.82
    67
    0.81
    65
    0.81
    26
    0.81
    21
    0.80
    37
    0.80
    Activations Density 0.016%

    No Known Activations