© 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. 9-RES-JB
    11. 14128
    Prev
    Next
    INDEX
    Explanations

    places or personnel related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    roles and titles related to organizational positions and responsibilities

    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
    animate
    -0.63
    ueless
    -0.59
    luster
    -0.58
     pedest
    -0.56
    venge
    -0.56
    Finish
    -0.56
    instead
    -0.55
     substitution
    -0.55
    ardless
    -0.53
    repeat
    -0.52
    POSITIVE LOGITS
     researcher
    0.82
     resear
    0.80
     consultancy
    0.78
     Architects
    0.75
     researchers
    0.74
     economist
    0.73
     analyst
    0.72
     analyses
    0.72
    alyses
    0.72
    research
    0.71
    Activations Density 0.498%

    No Known Activations