© 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. 10-RES-JB
    11. 10028
    Prev
    Next
    INDEX
    Explanations

    Web URLs and computer programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers related to artistic or creative elements, particularly in visual representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elim
    -0.78
     ingred
    -0.70
     satell
    -0.70
     advoc
    -0.69
     incorpor
    -0.69
     coh
    -0.69
     therap
    -0.68
     undermin
    -0.68
     surve
    -0.65
     coron
    -0.65
    POSITIVE LOGITS
     Pt
    0.77
    ebted
    0.71
    gt
    0.69
     srfAttach
    0.68
     partName
    0.67
    ivalent
    0.67
    ellen
    0.67
    ypes
    0.66
    td
    0.64
    ousel
    0.64
    Activations Density 0.248%

    No Known Activations