© 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. 6-RES-JB
    11. 11650
    Prev
    Next
    INDEX
    Explanations

    phrases related to morning television programs

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Morning Joe" program

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inates
    -0.91
    relative
    -0.74
    cial
    -0.73
    staking
    -0.69
    RED
    -0.69
    holes
    -0.69
    rero
    -0.68
    urally
    -0.67
    served
    -0.67
    rice
    -0.66
    POSITIVE LOGITS
     Morning
    0.89
     Caller
    0.88
    night
    0.84
    star
    0.80
    undown
    0.75
    aturdays
    0.74
     Evening
    0.74
    mares
    0.72
     Consult
    0.72
     Dew
    0.71
    Activations Density 0.020%

    No Known Activations