© 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. 22288
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Max" with a numerical value attached to it

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a specific name, likely "Max," in various contexts

    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
    vernment
    -0.78
    ilitary
    -0.77
    ribing
    -0.75
    uez
    -0.75
    lay
    -0.74
    alam
    -0.72
    bah
    -0.71
    Tea
    -0.70
    ahime
    -0.70
    kef
    -0.69
    POSITIVE LOGITS
     Max
    3.67
    Max
    3.19
     MAX
    2.06
    max
    2.05
     max
    1.90
    MAX
    1.85
     Maxim
    1.80
     Maxwell
    1.50
     Maximum
    1.41
     Chloe
    1.37
    Activations Density 0.017%

    No Known Activations