© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    mentions of news agencies or media outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Associated Press

    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
    gone
    -0.93
    orously
    -0.78
    tty
    -0.75
    ettel
    -0.68
    itars
    -0.68
    fighting
    -0.67
    steen
    -0.66
    fare
    -0.65
    wagen
    -0.64
    lda
    -0.64
    POSITIVE LOGITS
     Press
    1.00
     Newsp
    0.86
     Arbit
    0.84
     States
    0.82
     Colleg
    0.82
     Franch
    0.79
    Choice
    0.72
     Images
    0.72
     Tribune
    0.71
     Nations
    0.71
    Activations Density 0.017%

    No Known Activations