© 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. 10-RES-JB
    11. 10180
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sensational or controversial topics

    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
     organis
    -0.85
     organised
    -0.81
     bes
    -0.79
     humour
    -0.79
     armour
    -0.78
     ageing
    -0.77
     prey
    -0.76
     armoured
    -0.75
     civilisation
    -0.73
     organising
    -0.72
    POSITIVE LOGITS
    Enlarge
    1.81
    toggle
    1.59
    NPR
    1.14
    WASHINGTON
    1.06
    Breaking
    1.06
    Tweet
    1.05
    EX
    1.04
    hello
    1.04
    Photo
    1.03
    FOX
    1.00
    Activations Density 0.093%

    No Known Activations