© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8705
    Prev
    Next
    INDEX
    Explanations

    web development-related code snippets and URLs

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and syntax related to web development and databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drying
    -0.86
     leaps
    -0.85
     dismantling
    -0.85
     mechanically
    -0.85
     paralysis
    -0.84
     adaptations
    -0.83
     clamp
    -0.83
     seams
    -0.82
     harsher
    -0.80
     landsl
    -0.79
    POSITIVE LOGITS
    username
    1.55
    example
    1.43
    76561
    1.43
    NAME
    1.41
    ername
    1.38
    USER
    1.35
     username
    1.35
     Username
    1.30
    password
    1.26
    domain
    1.24
    Activations Density 0.470%

    No Known Activations