© 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. 21799
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers and degrees

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or legal power

    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
    matic
    -0.72
     apes
    -0.67
     lapse
    -0.62
     Tanz
    -0.62
     flowering
    -0.61
    ulative
    -0.60
     pigeon
    -0.60
     steps
    -0.60
     meditation
    -0.59
     reflex
    -0.59
    POSITIVE LOGITS
    ï¸ı
    1.10
    âĵĺ
    0.90
    ield
    0.89
    arthed
    0.88
    ever
    0.83
    reci
    0.81
    âĶĢâĶĢ
    0.79
    ternity
    0.77
    bryce
    0.77
    vernment
    0.76
    Activations Density 0.153%

    No Known Activations