© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17713
    Prev
    Next
    INDEX
    Explanations

    locations and dates mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    numerical and location references within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -1.43
     Whilst
    -1.27
     util
    -1.09
     independ
    -0.89
    Firstly
    -0.89
     ðŁĻĤ
    -0.86
     secondly
    -0.85
     recognise
    -0.85
     organisation
    -0.83
     fantastic
    -0.82
    POSITIVE LOGITS
    ___
    1.25
    Newsletter
    1.00
    earchers
    0.95
     Calif
    0.94
     POLITICO
    0.91
    vernment
    0.89
     nonprofit
    0.84
     spokeswoman
    0.82
     cellphone
    0.82
    CLOSE
    0.80
    Activations Density 2.616%

    No Known Activations