© 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. 8-RES-JB
    11. 6123
    Prev
    Next
    INDEX
    Explanations

    references to media and press related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the media's influence and control over information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.77
     Solitaire
    -0.76
    ģĸ
    -0.74
     Calculator
    -0.70
     Builder
    -0.69
    »Ĵ
    -0.64
     Yamato
    -0.64
     Achieve
    -0.64
     Plans
    -0.63
     inherit
    -0.63
    POSITIVE LOGITS
     biased
    0.96
     obsc
    0.93
    reporting
    0.92
     portraying
    0.86
    biased
    0.85
     dissemin
    0.82
     outlets
    0.81
     broadcasting
    0.81
    annels
    0.81
    orters
    0.80
    Activations Density 0.730%

    No Known Activations