Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8378
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically focusing on 'Hassan'

    oai_token-act-pair · gpt-3.5-turbo

    names related to prominent figures, particularly those with the first name "Hassan"

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

    No Comments

    Negative Logits
    çĦ
    -0.69
    BuyableInstoreAndOnline
    -0.67
    fare
    -0.67
     canine
    -0.65
    ridor
    -0.64
    tted
    -0.62
    culosis
    -0.62
    chrom
    -0.62
    onomy
    -0.61
    chest
    -0.60
    POSITIVE LOGITS
     Rouhani
    1.15
     Hassan
    1.00
     Whites
    0.89
    daq
    0.87
    anni
    0.79
    xual
    0.78
    etics
    0.78
    emaker
    0.77
    emet
    0.77
    ascus
    0.73
    Activations Density 0.008%

    No Known Activations