© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    numerical values such as quantities and measurements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to analysis or critique of historical or contemporary events

    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
     secondly
    -0.62
     whilst
    -0.60
    jriwal
    -0.59
     the
    -0.57
     Whilst
    -0.57
     tha
    -0.53
     realise
    -0.52
     THE
    -0.50
     Secondly
    -0.50
    the
    -0.49
    POSITIVE LOGITS
     stiffness
    0.56
    zens
    0.51
    dozen
    0.50
     sexes
    0.45
    ailed
    0.45
    weapons
    0.43
    ahl
    0.43
    ogly
    0.42
     pounding
    0.42
    IONS
    0.41
    Activations Density 1.043%

    No Known Activations