© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3690
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and dominance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of control or managing various aspects of systems or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zig
    -0.77
     Blessed
    -0.73
    nee
    -0.68
    ISS
    -0.67
    çĦ
    -0.66
     Vide
    -0.65
    Else
    -0.65
    bp
    -0.65
    jen
    -0.65
     Hitman
    -0.64
    POSITIVE LOGITS
     controlling
    1.14
     controlled
    1.01
    eering
    0.97
     controls
    0.85
     impulses
    0.83
    controlled
    0.83
    anova
    0.82
    essee
    0.82
    urable
    0.82
     personalities
    0.81
    Activations Density 0.009%

    No Known Activations