© 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. 9-RES-JB
    11. 18465
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political contexts and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alto
    -0.61
    flush
    -0.59
    stadt
    -0.59
    leasing
    -0.58
    alone
    -0.56
     Weber
    -0.56
    tails
    -0.55
    Mist
    -0.55
    Desktop
    -0.54
    door
    -0.54
    POSITIVE LOGITS
     correctness
    0.75
     speeches
    0.69
    ndum
    0.67
    clinton
    0.65
     pamph
    0.63
     slogans
    0.61
    aroo
    0.61
    xual
    0.61
    EStream
    0.60
     hostage
    0.60
    Activations Density 0.600%

    No Known Activations