Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12499
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to pursuit or tracking someone/something down

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tracking and arresting individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jab
    -0.78
    Cola
    -0.77
     pane
    -0.76
    enum
    -0.75
    wcs
    -0.72
    interstitial
    -0.71
    paren
    -0.68
    placed
    -0.68
     palate
    -0.65
    uph
    -0.65
    POSITIVE LOGITS
     informants
    0.90
     burgl
    0.86
     suspects
    0.85
     Detective
    0.79
     sightings
    0.79
     UFOs
    0.78
     Victims
    0.78
     robbers
    0.77
     RCMP
    0.77
     terrorists
    0.75
    Activations Density 0.163%

    No Known Activations