© 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. 0-RES-JB
    11. 11262
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Envy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Envy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturdays
    -0.87
    AAAAAAAA
    -0.84
    iband
    -0.70
    weight
    -0.68
    sonian
    -0.67
    urai
    -0.66
    tale
    -0.65
    wark
    -0.65
    VB
    -0.65
    bush
    -0.64
    POSITIVE LOGITS
     En
    3.52
    En
    2.33
     EN
    1.69
     Ens
    1.63
     en
    1.54
     Enc
    1.30
     Des
    1.18
     Enchant
    1.10
     Ent
    1.09
    en
    1.07
    Activations Density 0.020%

    No Known Activations