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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24408
    Prev
    Next
    INDEX
    Explanations

    financial-related terms and numbers

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to media attention and controversies surrounding public figures

    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
    --+
    -0.86
    anqu
    -0.84
    uncture
    -0.82
    ivot
    -0.78
    rastructure
    -0.78
    anship
    -0.77
    -|
    -0.77
    Region
    -0.75
    cture
    -0.74
    Ö
    -0.74
    POSITIVE LOGITS
     prank
    1.25
     spoof
    1.23
     hoax
    1.22
     parody
    1.18
     porn
    1.16
     pedoph
    1.15
     TMZ
    1.13
     satirical
    1.12
     pornographic
    1.11
     homophobic
    1.11
    Activations Density 1.082%

    No Known Activations