© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6324
    Prev
    Next
    INDEX
    Explanations

    phrases related to influence and impact

    oai_token-act-pair · gpt-3.5-turbo

    references to influence and its impact on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owler
    -0.71
    unic
    -0.71
    gey
    -0.69
    NB
    -0.68
    oaded
    -0.68
    itten
    -0.66
    ci
    -0.66
    thens
    -0.64
    solete
    -0.64
    quished
    -0.63
    POSITIVE LOGITS
     outcome
    1.53
     outcomes
    1.26
     trajectory
    1.23
     behaviour
    1.20
     fate
    1.19
     perception
    1.18
     behavior
    1.17
     likelihood
    1.17
     effectiveness
    1.15
     way
    1.13
    Activations Density 0.223%

    No Known Activations