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. 10-RES-JB
    6. 9519
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate fear or concern regarding potential risks or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cember
    -0.83
     Tycoon
    -0.75
    çͰ
    -0.74
    borgh
    -0.73
    UFC
    -0.72
    rican
    -0.71
    Donald
    -0.69
    Rated
    -0.69
    razil
    -0.67
    usterity
    -0.67
    POSITIVE LOGITS
     theirs
    0.93
     nuance
    0.91
     such
    0.87
     specifics
    0.86
     caveats
    0.86
     particulars
    0.85
     things
    0.84
     insights
    0.82
     anything
    0.80
     broader
    0.80
    Activations Density 0.937%

    No Known Activations