© 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. 14550
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives suggesting a level of closeness or similarity to a certain degree

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remote control and vague descriptions of actions or conditions

    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
    glers
    -0.80
     selection
    -0.72
    oise
    -0.67
     Parenthood
    -0.66
     cardinal
    -0.65
     Spani
    -0.65
    uese
    -0.63
     Reef
    -0.63
     Selection
    -0.63
    ters
    -0.63
    POSITIVE LOGITS
     resembling
    0.93
     entertained
    0.91
     situated
    0.88
     conceived
    0.82
    ONSORED
    0.80
     resembled
    0.77
     construed
    0.76
    TPPStreamerBot
    0.76
    ĪĴ
    0.76
     impressed
    0.74
    Activations Density 0.031%

    No Known Activations