© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18777
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing reassurance or asserting something confidently

    oai_token-act-pair · gpt-3.5-turbo

    terms related to assertion and confirmation of beliefs or statuses

    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
    chain
    -0.68
     spoil
    -0.66
    gom
    -0.66
     Filipino
    -0.62
     Daniels
    -0.61
     Horse
    -0.60
     bearer
    -0.59
     chain
    -0.58
     Kafka
    -0.57
     tongues
    -0.56
    POSITIVE LOGITS
    issance
    1.12
    uation
    1.09
    ension
    1.08
    irmation
    1.07
    essional
    1.04
    formation
    1.02
    essment
    0.99
    ishment
    0.97
    urances
    0.97
    essed
    0.94
    Activations Density 0.051%

    No Known Activations