© 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. 4-RES-JB
    11. 6452
    Prev
    Next
    INDEX
    Explanations

    verbs indicating attempts or actions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and attempts

    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
    ombat
    -0.78
    oot
    -0.70
    uminati
    -0.68
    efer
    -0.67
    pdf
    -0.66
    oha
    -0.66
    cmp
    -0.66
    umm
    -0.63
    aign
    -0.63
    mp
    -0.63
    POSITIVE LOGITS
    conservancy
    0.73
    redients
    0.65
    LESS
    0.65
     Provided
    0.63
     conduc
    0.63
     orphans
    0.63
     assignments
    0.60
    ctors
    0.59
     aside
    0.58
     crowds
    0.58
    Activations Density 0.228%

    No Known Activations