© 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. 14076
    Prev
    Next
    INDEX
    Explanations

    phrases related to sensitive information or topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sensitive topics or issues

    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
    mania
    -0.69
     Wolver
    -0.66
    swick
    -0.66
    hang
    -0.66
    ulhu
    -0.65
    amaz
    -0.64
    anova
    -0.63
    corn
    -0.62
    ellen
    -0.62
    solete
    -0.62
    POSITIVE LOGITS
    ivities
    1.16
     sensitive
    1.00
     sensit
    0.89
    ly
    0.83
     sensibilities
    0.82
     emotions
    0.82
     sensitivity
    0.81
    sensitive
    0.80
    mble
    0.79
     proble
    0.79
    Activations Density 0.039%

    No Known Activations