© 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. 7-RES-JB
    11. 23766
    Prev
    Next
    INDEX
    Explanations

    words related to magic wands

    oai_token-act-pair · gpt-3.5-turbo

    references to wands and magical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.82
     unbeliev
    -0.76
    £ı
    -0.73
    ccording
    -0.71
    tics
    -0.70
    ©¶æ
    -0.68
    xual
    -0.67
    vironments
    -0.67
     exha
    -0.66
    Ļ½
    -0.66
    POSITIVE LOGITS
    erers
    1.53
    erer
    1.49
    glers
    0.98
    icular
    0.88
    ering
    0.86
    inal
    0.84
    fold
    0.84
    ring
    0.80
    ulla
    0.80
    wright
    0.80
    Activations Density 0.068%

    No Known Activations