© 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. 9-RES-JB
    11. 1952
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of impacts on different entities or systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the effects and impacts of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknowled
    -0.70
    wagen
    -0.65
    ft
    -0.63
    serv
    -0.61
    atts
    -0.60
    Ĥ¬
    -0.59
     ropes
    -0.57
     Sins
    -0.57
    Vs
    -0.56
    orks
    -0.56
    POSITIVE LOGITS
     impacting
    0.95
     affecting
    0.92
     impact
    0.85
     multiplier
    0.83
     ripple
    0.82
     reverber
    0.82
     upon
    0.80
     shaping
    0.80
     affect
    0.80
     impacts
    0.77
    Activations Density 0.135%

    No Known Activations