© 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. 5584
    Prev
    Next
    INDEX
    Explanations

    phrases related to approval or disapproval

    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
    rone
    -0.78
    eor
    -0.72
    quist
    -0.72
    rol
    -0.68
    OTAL
    -0.67
    ersen
    -0.65
    llular
    -0.65
    ttes
    -0.65
    asers
    -0.64
    artments
    -0.64
    POSITIVE LOGITS
     embod
    1.12
     well
    1.04
     follows
    1.02
     opposed
    1.01
    pires
    1.01
     belonging
    0.96
     being
    0.93
     occurring
    0.92
     synonymous
    0.91
     evidenced
    0.90
    Activations Density 0.149%

    No Known Activations