© 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. 14613
    Prev
    Next
    INDEX
    Explanations

    phrases that are introductions to issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    statements concerning problems or issues

    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
    amins
    -0.76
    haw
    -0.75
    ledged
    -0.74
    rug
    -0.71
    throp
    -0.70
    cyclop
    -0.69
    emies
    -0.69
    onga
    -0.69
    uries
    -0.65
    chel
    -0.65
    POSITIVE LOGITS
     plag
    0.87
     worsened
    0.75
     arising
    0.74
     arise
    0.72
     unresolved
    0.71
     exacerbated
    0.70
     miscon
    0.68
     Fowler
    0.67
     arises
    0.67
     compounded
    0.64
    Activations Density 0.528%

    No Known Activations