© 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. 13801
    Prev
    Next
    INDEX
    Explanations

    phrases related to an excessive amount of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "too much."

    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
    ospels
    -0.92
    ħĭ
    -0.91
    ades
    -0.91
    endants
    -0.89
    ologies
    -0.88
    rings
    -0.82
    geons
    -0.81
    sets
    -0.80
    saf
    -0.80
    atures
    -0.79
    POSITIVE LOGITS
     attention
    1.18
     emphasis
    1.06
     downtime
    1.02
     scrutiny
    0.98
     information
    0.98
     autonomy
    0.98
     firepower
    0.95
     variability
    0.94
     negativity
    0.94
     effort
    0.93
    Activations Density 0.157%

    No Known Activations