© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    references to actions directed towards objects or individuals

    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
    cair
    -0.69
     Niet
    -0.68
    Avg
    -0.68
    utm
    -0.67
    how
    -0.66
    tnc
    -0.64
    verages
    -0.62
     hrs
    -0.62
    cean
    -0.61
    omore
    -0.61
    POSITIVE LOGITS
     available
    1.01
     aware
    0.96
     disappear
    0.96
     accessible
    0.95
     unavailable
    0.93
     happen
    0.91
     compulsory
    0.89
     acquainted
    0.89
     vanish
    0.87
     dependent
    0.86
    Activations Density 0.153%

    No Known Activations