© 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. 4332
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and activism

    oai_token-act-pair · gpt-3.5-turbo
    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
    ebin
    -0.64
    icut
    -0.63
    ouple
    -0.62
     Leilan
    -0.58
    ificant
    -0.58
     =================================================================
    -0.57
    ajor
    -0.57
    wallet
    -0.57
    é¾įåĸļ士
    -0.55
    DN
    -0.55
    POSITIVE LOGITS
     envisioned
    0.89
     that
    0.83
     required
    0.82
     depicted
    0.80
     envis
    0.76
    that
    0.76
     plag
    0.75
     which
    0.75
     portrayed
    0.75
    which
    0.74
    Activations Density 0.868%

    No Known Activations