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. 6-RES-JB
    6. 4776
    Prev
    Next
    INDEX
    Explanations

    words related to floods, legal terms, and security

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to legal matters and law enforcement

    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
    ©¶æ¥µ
    -0.69
    nikov
    -0.68
    ij士
    -0.67
    CHR
    -0.65
    ¢
    -0.63
    ¿½
    -0.60
    ALSE
    -0.59
     heirs
    -0.59
    ĨĴ
    -0.58
     hostages
    -0.58
    POSITIVE LOGITS
    monary
    0.82
    enaries
    0.71
    nels
    0.66
    izont
    0.66
    finder
    0.64
    estern
    0.64
     Detected
    0.63
     abdom
    0.62
     ponds
    0.62
    alore
    0.62
    Activations Density 0.723%

    No Known Activations