© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2691
    Prev
    Next
    INDEX
    Explanations

    dates and locations in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "in" and related spatial or temporal phrases

    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
     clipboard
    -0.70
    emo
    -0.68
     abound
    -0.63
    endif
    -0.62
    âĨij
    -0.61
     survives
    -0.60
    mentioned
    -0.59
    dll
    -0.59
    framework
    -0.59
    fml
    -0.59
    POSITIVE LOGITS
     Maiden
    0.76
    rocal
    0.72
    roc
    0.68
    ISON
    0.66
     commem
    0.64
     Spokane
    0.62
     Marble
    0.61
     Springer
    0.61
    igslist
    0.60
    QUI
    0.59
    Activations Density 0.398%

    No Known Activations