© 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. 2165
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a particular point or argument

    oai_token-act-pair · gpt-3.5-turbo

    the word "So" used to introduce explanations or conclusions

    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
    saf
    -0.66
    thro
    -0.63
     ``(
    -0.61
     nic
    -0.59
    ¢
    -0.58
     Halls
    -0.56
    âĹ¼
    -0.55
     Purg
    -0.55
     [[
    -0.54
    ski
    -0.54
    POSITIVE LOGITS
    oner
    1.25
    bered
    1.01
    fter
    0.99
    FTWARE
    0.98
    apy
    0.95
    oths
    0.91
    othes
    0.90
    ooo
    0.90
    aps
    0.86
    aked
    0.84
    Activations Density 0.061%

    No Known Activations