© 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. 5195
    Prev
    Next
    INDEX
    Explanations

    terms related to computer coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    references to errors and defects

    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
    anwhile
    -0.80
     recording
    -0.67
     collecting
    -0.66
     scatter
    -0.66
     collect
    -0.64
    market
    -0.62
     COP
    -0.61
     reception
    -0.60
     visitor
    -0.60
    perse
    -0.60
    POSITIVE LOGITS
    ¡
    1.20
    º
    1.19
    ¤
    1.15
    Ĵ
    1.14
    ¬
    1.14
    ĵ
    1.12
    Ī
    1.11
    ¶
    1.09
    ¼
    1.07
    ¥
    1.06
    Activations Density 0.295%

    No Known Activations