© 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. 11-RES-JB
    11. 20652
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What do you think/make of" followed by a topic or situation for interpretation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve asking for opinions or evaluations about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.92
    eful
    -0.76
    cue
    -0.73
    ulo
    -0.73
    âĸij
    -0.72
    vity
    -0.71
    chnology
    -0.71
    efully
    -0.71
    ority
    -0.69
    ittal
    -0.68
    POSITIVE LOGITS
     them
    1.10
     him
    1.01
     these
    0.95
     this
    0.90
     us
    0.89
     yourselves
    0.89
     ourselves
    0.87
     THEM
    0.83
     Them
    0.82
     those
    0.78
    Activations Density 0.191%

    No Known Activations