© 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. 6910
    Prev
    Next
    INDEX
    Explanations

    articles marked by a specific symbol and following information relevant to the content as indicated by the symbol

    oai_token-act-pair · gpt-3.5-turbo

    author names and publication dates

    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
     refunds
    -0.70
     incub
    -0.69
     rightful
    -0.67
     decap
    -0.66
     torped
    -0.66
     raiding
    -0.64
     realised
    -0.63
     Unic
    -0.62
     susp
    -0.62
     deciding
    -0.62
    POSITIVE LOGITS
    BBC
    1.32
    Editor
    1.06
    Narr
    1.01
    Associated
    0.98
    Guest
    0.96
    EVA
    0.92
    CNN
    0.91
    Contribut
    0.91
    Originally
    0.90
    WASHINGTON
    0.89
    Activations Density 0.093%

    No Known Activations