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. 2-RES-JB
    6. 20655
    Prev
    Next
    INDEX
    Explanations

    adjectives describing negative characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unacknowledged or involuntary actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.82
    anwhile
    -0.78
    hyde
    -0.76
    ĺħ
    -0.75
    onyms
    -0.73
    senal
    -0.72
     Defenders
    -0.71
    uyomi
    -0.71
    oples
    -0.69
    pmwiki
    -0.67
    POSITIVE LOGITS
    ritten
    1.01
    arranted
    0.98
    inding
    0.93
    ashed
    0.91
    ield
    0.89
    irth
    0.87
    avering
    0.85
    itt
    0.83
    ishable
    0.82
    atcher
    0.81
    Activations Density 0.004%

    No Known Activations