© 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. 3-RES-JB
    11. 17900
    Prev
    Next
    INDEX
    Explanations

    words related to environmental issues and political titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the terms related to environmental and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gging
    -0.68
    tt
    -0.66
     Pearce
    -0.66
     mamm
    -0.66
     Pwr
    -0.65
    âĺħâĺħ
    -0.61
     custody
    -0.60
     marrow
    -0.60
    ffen
    -0.59
     mammoth
    -0.58
    POSITIVE LOGITS
    ial
    1.50
    hip
    1.44
    alist
    1.34
    edIn
    1.24
    ional
    1.23
    ially
    1.17
    al
    1.17
    icipated
    1.12
    ions
    1.09
    atile
    1.08
    Activations Density 0.057%

    No Known Activations