© 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 EvalsExportsinterp-engineNEWAPI 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. 5609
    Prev
    Next
    INDEX
    Explanations

    words related to size or quantity, particularly emphasizing that something is 'large enough'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sufficient size or capacity

    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
     Guth
    -0.79
    Brow
    -0.71
    amily
    -0.70
    bull
    -0.70
    misc
    -0.66
    zl
    -0.65
    analysis
    -0.64
    cot
    -0.63
    anton
    -0.63
    tell
    -0.63
    POSITIVE LOGITS
    hots
    0.67
     quantities
    0.63
     ILCS
    0.62
     persuasive
    0.61
    andem
    0.61
     sidx
    0.61
     doses
    0.59
    rehend
    0.59
    -+-+
    0.58
     detectable
    0.58
    Activations Density 0.021%

    No Known Activations