© 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. 4-RES-JB
    11. 16629
    Prev
    Next
    INDEX
    Explanations

    terms related to praise or criticism

    oai_token-act-pair · gpt-3.5-turbo

    words related to themes of extremism or extreme actions

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

    No Comments

    Negative Logits
    gerald
    -0.74
     Labrador
    -0.70
     McCabe
    -0.66
     behold
    -0.66
     McF
    -0.65
     Cue
    -0.63
     Flan
    -0.62
     Ack
    -0.59
     modern
    -0.59
     Angus
    -0.58
    POSITIVE LOGITS
    nants
    1.08
    ovable
    1.05
    nant
    1.05
    ploy
    1.02
    antle
    1.00
    phasis
    0.98
    arkable
    0.94
    oval
    0.91
    acy
    0.91
    asons
    0.91
    Activations Density 0.013%

    No Known Activations