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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 4731
    Prev
    Next
    INDEX
    Explanations

    individuals' actions and their involvement in specific events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and related forms that indicate past actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipeg
    -0.75
    PsyNetMessage
    -0.75
    iann
    -0.72
    izable
    -0.71
    oidal
    -0.71
     certs
    -0.69
    inav
    -0.68
    idth
    -0.68
    icles
    -0.67
    ties
    -0.66
    POSITIVE LOGITS
     coerced
    1.26
     misled
    1.21
     negligent
    1.18
     pressured
    1.12
     victimized
    1.11
     deceived
    1.10
     complicit
    1.10
     wrongly
    1.09
     unaware
    1.09
     manipulated
    1.07
    Activations Density 0.267%

    No Known Activations