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. 3-RES-JB
    6. 2370
    Prev
    Next
    INDEX
    Explanations

    code snippets related to updating or removing user data in a database

    oai_token-act-pair · gpt-3.5-turbo

    coding-related terms associated with user management and database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warranties
    -0.68
     arsen
    -0.66
    ecause
    -0.65
    accompan
    -0.65
    Æ
    -0.65
     positively
    -0.61
     addictive
    -0.60
     sides
    -0.60
     ANG
    -0.59
     gearing
    -0.58
    POSITIVE LOGITS
    _
    1.12
    tenance
    0.98
    buf
    0.81
    Header
    0.81
    obj
    0.80
    __
    0.79
    Flags
    0.78
    Instance
    0.78
    Info
    0.77
    uments
    0.74
    Activations Density 0.240%

    No Known Activations