© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    actions of passing or delivering items to specific recipients

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "to."

    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
     wrinkles
    -0.78
    ively
    -0.71
     risks
    -0.71
     disruptions
    -0.70
     arrests
    -0.69
    iveness
    -0.68
    tions
    -0.68
     exposures
    -0.65
     vows
    -0.64
     ante
    -0.64
    POSITIVE LOGITS
    pload
    0.97
    ggles
    0.88
    ilet
    0.85
     satisfy
    0.78
    MRI
    0.75
    ISC
    0.74
    othy
    0.73
     accompany
    0.72
    psy
    0.71
     fulfill
    0.70
    Activations Density 0.167%

    No Known Activations