© 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. 7-RES-JB
    11. 1690
    Prev
    Next
    INDEX
    Explanations

    country names followed by a symbol related to news or politics

    oai_token-act-pair · gpt-3.5-turbo

    certain symbols or characters that indicate specific categories of reports or statements regarding nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blond
    -0.67
    isode
    -0.66
     giveaways
    -0.66
     microphone
    -0.66
     yarn
    -0.66
     giveaway
    -0.65
    ronic
    -0.65
     treadmill
    -0.64
     litter
    -0.64
     discs
    -0.63
    POSITIVE LOGITS
    ¬
    1.15
    £
    1.07
    ¹
    1.01
    º
    0.98
    ħ
    0.98
    ¸
    0.96
    ²
    0.96
    AFP
    0.95
    ®
    0.95
    ı
    0.95
    Activations Density 0.246%

    No Known Activations