© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    references to meetings or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "Meet" and "meet up" concepts

    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
    wcs
    -0.75
    vernment
    -0.71
    structed
    -0.65
     annexed
    -0.62
     controlling
    -0.61
    etheless
    -0.60
     coating
    -0.58
     shroud
    -0.57
     untreated
    -0.56
     indictment
    -0.56
    POSITIVE LOGITS
    ups
    1.18
    up
    1.16
    ings
    1.06
    amorph
    0.90
    agame
    0.87
    UP
    0.84
    ropolis
    0.83
     ups
    0.77
    tle
    0.77
    ees
    0.77
    Activations Density 0.032%

    No Known Activations