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. 4926
    Prev
    Next
    INDEX
    Explanations

    menu options and features related to software settings

    oai_token-act-pair · gpt-3.5-turbo

    technical instructions related to software interactions

    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
    vec
    -1.02
    tumblr
    -0.86
    dor
    -0.81
    phil
    -0.79
    bent
    -0.79
    pher
    -0.76
    spir
    -0.75
    hur
    -0.75
    bane
    -0.74
    phen
    -0.73
    POSITIVE LOGITS
     login
    1.07
     uninstall
    1.05
     settings
    0.98
     toggle
    0.95
     permissions
    0.95
     presets
    0.94
     plugin
    0.93
     overwrite
    0.93
     controls
    0.91
     override
    0.91
    Activations Density 0.592%

    No Known Activations