© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights, power, and limitations

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and privileges regarding personal freedoms

    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
     Scenes
    -0.74
    naires
    -0.71
     reactions
    -0.68
     Emails
    -0.67
     Zeit
    -0.66
     Atmosp
    -0.65
    phrine
    -0.65
     forecasting
    -0.64
     Tracks
    -0.63
    ODY
    -0.62
    POSITIVE LOGITS
     conferred
    1.37
     bestowed
    1.31
     reserved
    1.21
     granted
    1.21
     vested
    1.17
     revoked
    1.11
     afforded
    1.10
     relinqu
    1.09
    ©¶æ¥µ
    1.05
     coveted
    1.03
    Activations Density 0.374%

    No Known Activations