© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "going"

    oai_token-act-pair · gpt-3.5-turbo

    the word "going" in various contexts

    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
    ullah
    -0.92
    lake
    -0.72
    ament
    -0.72
     Horus
    -0.72
    lain
    -0.68
    uminati
    -0.67
    icone
    -0.63
    ificent
    -0.62
    ilitarian
    -0.62
    ifully
    -0.62
    POSITIVE LOGITS
     forward
    0.87
    Ń·
    0.87
    verning
    0.84
    ©¶æ
    0.84
    lems
    0.83
    vt
    0.81
    ãĥ£
    0.81
     forwards
    0.79
     viral
    0.76
     Away
    0.75
    Activations Density 0.047%

    No Known Activations