© 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. 9865
    Prev
    Next
    INDEX
    Explanations

    specific instances of a measure or quantity related to consumption or production

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify amounts or rates per specified units

    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
    hess
    -0.79
    ITED
    -0.74
    çīĪ
    -0.71
    çĶ°
    -0.69
    enegger
    -0.69
     GOODMAN
    -0.68
    XT
    -0.67
    ARDIS
    -0.66
    ESCO
    -0.66
    ãĤ¦ãĤ¹
    -0.65
    POSITIVE LOGITS
     capita
    1.36
    tains
    1.13
    malink
    1.01
    versely
    0.91
    ishable
    0.90
     hour
    0.88
    secut
    0.86
    missive
    0.86
     month
    0.86
    uvian
    0.86
    Activations Density 0.032%

    No Known Activations