© 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. 0-RES-JB
    11. 1212
    Prev
    Next
    INDEX
    Explanations

    phrases related to "Mag" or "Magazine."

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to a specific magazine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icago
    -0.69
     Haley
    -0.68
    ledged
    -0.67
    olson
    -0.66
    zee
    -0.66
    HAHA
    -0.66
    _>
    -0.66
    uffer
    -0.65
    neys
    -0.65
    CLOSE
    -0.65
    POSITIVE LOGITS
     Mag
    3.85
    Mag
    2.90
     mag
    2.56
    mag
    2.10
     MAG
    1.73
    MAG
    1.46
     Magnet
    1.45
    Magn
    1.37
     magnesium
    1.36
     magistrate
    1.36
    Activations Density 0.010%

    No Known Activations