© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 23635
    Prev
    Next
    INDEX
    Explanations

    verbs related to asking or requesting someone to perform an action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "asked to" followed by actions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appears
    -0.68
    ////////////////////////////////
    -0.65
    requires
    -0.61
    productive
    -0.60
    etheless
    -0.60
    tions
    -0.60
     Needs
    -0.60
    abiding
    -0.59
     Died
    -0.59
    alde
    -0.59
    POSITIVE LOGITS
     participate
    1.12
     clarify
    1.09
     nominate
    1.07
     join
    1.02
     accompany
    1.00
     partake
    0.99
     postpone
    0.99
     give
    0.97
     perform
    0.96
     intervene
    0.96
    Activations Density 0.080%

    No Known Activations