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

    Neuronpedia

    Jacobian LensNEW
    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. 7781
    Prev
    Next
    INDEX
    Explanations

    words related to rivalry or opposition

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and suffixes related to political and dramatic themes

    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
    igue
    -0.70
     Spartans
    -0.68
    iage
    -0.67
    aukee
    -0.63
    aceae
    -0.62
    enthal
    -0.62
    icans
    -0.62
     outp
    -0.61
    hemy
    -0.61
    agascar
    -0.60
    POSITIVE LOGITS
    ulhu
    0.89
    Rect
    0.77
    otide
    0.71
    äºĶ
    0.69
    Breaking
    0.67
    Pacific
    0.65
    ĪĴ
    0.64
    Jun
    0.64
    士
    0.64
    Bell
    0.64
    Activations Density 0.244%

    No Known Activations