© 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. 3-RES-JB
    11. 24358
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of maturity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "nature" and its various forms and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bows
    -0.79
    ista
    -0.77
    Il
    -0.71
    tons
    -0.69
    OWS
    -0.69
    igi
    -0.68
    elcome
    -0.67
    oran
    -0.61
    ãĤ¦ãĤ¹
    -0.60
    Bey
    -0.60
    POSITIVE LOGITS
    ature
    1.27
    atures
    1.03
     corrections
    0.67
    xus
    0.67
     Peninsula
    0.65
    ity
    0.64
    vity
    0.63
    smanship
    0.63
    entric
    0.63
     hippocamp
    0.63
    Activations Density 0.014%

    No Known Activations