© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20279
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative outcomes, challenges, or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating addition or connection

    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
    ULTS
    -0.89
    ESE
    -0.80
     Lines
    -0.79
     Dreams
    -0.76
    ODY
    -0.76
    verts
    -0.75
     Walls
    -0.73
    ICES
    -0.72
    ults
    -0.72
     Pigs
    -0.71
    POSITIVE LOGITS
    rogen
    1.07
     lucrative
    1.06
     costly
    1.05
     outspoken
    1.03
     influential
    1.01
     nuanced
    1.01
     mutually
    1.00
     profitable
    1.00
     expensive
    0.99
     powerful
    0.99
    Activations Density 0.105%

    No Known Activations