© 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. 19803
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    possessive constructions indicating ownership or relation to a subject

    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
    este
    -0.84
    wright
    -0.82
    lain
    -0.76
    then
    -0.74
    ova
    -0.74
    naires
    -0.73
    usa
    -0.72
    bows
    -0.71
    handedly
    -0.71
    VO
    -0.71
    POSITIVE LOGITS
     announcement
    0.94
     edition
    0.88
     arrival
    0.83
     episode
    0.81
     installment
    0.78
     deadline
    0.76
     Courier
    0.75
     landmark
    0.75
     morning
    0.74
     unveiling
    0.74
    Activations Density 0.043%

    No Known Activations