© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong position or opinion on a subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate expression or communication of thoughts and ideas

    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
    riger
    -0.73
    nce
    -0.65
    croft
    -0.63
    irection
    -0.61
    authorized
    -0.60
     invaders
    -0.59
    washer
    -0.58
    itary
    -0.58
     rift
    -0.58
    cephal
    -0.58
    POSITIVE LOGITS
     offer
    0.94
     contribute
    0.93
     prove
    0.88
     learn
    0.88
     contend
    0.86
     say
    0.85
     teach
    0.81
     apologize
    0.81
     impart
    0.80
     SAY
    0.76
    Activations Density 0.050%

    No Known Activations