© 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. 10-RES-JB
    11. 16404
    Prev
    Next
    INDEX
    Explanations

    phrases related to handing over or transferring items or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transferring or giving up control of something

    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
    embed
    -0.76
    nis
    -0.73
    vic
    -0.67
    aho
    -0.67
    odox
    -0.66
    Semitism
    -0.65
    iste
    -0.64
    andem
    -0.64
    Compar
    -0.63
    oun
    -0.62
    POSITIVE LOGITS
     control
    1.11
    control
    0.94
     ownership
    0.93
     reins
    0.93
     custody
    0.93
     responsibility
    0.91
     keys
    0.89
     sovereignty
    0.89
     CONTROL
    0.86
     secrets
    0.85
    Activations Density 0.118%

    No Known Activations