© 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. 6-RES-JB
    11. 20598
    Prev
    Next
    INDEX
    Explanations

    phrases related to "fire"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ire."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.91
    ļé
    -0.89
    romeda
    -0.85
    ¬¼
    -0.81
    ĨĴ
    -0.80
     carbohyd
    -0.80
    acca
    -0.74
    atform
    -0.72
    sylv
    -0.72
    achusetts
    -0.71
    POSITIVE LOGITS
    nces
    1.09
    lli
    1.02
    ttes
    0.93
    lessly
    0.92
    ly
    0.88
    ndra
    0.86
    lla
    0.85
    brand
    0.84
    lette
    0.83
    zza
    0.82
    Activations Density 0.035%

    No Known Activations