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. 9-RES-JB
    6. 6370
    Prev
    Next
    INDEX
    Explanations

    phrases related to political visits and actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "is" and its variants in various contexts

    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
    acters
    -0.79
     deform
    -0.74
     clicks
    -0.70
    PsyNetMessage
    -0.69
     occurrences
    -0.66
     Occupations
    -0.66
     triangles
    -0.66
     Triangle
    -0.65
     reproduction
    -0.65
     samples
    -0.65
    POSITIVE LOGITS
     reluctant
    1.14
     impe
    1.11
     tempted
    1.10
     briefed
    1.10
     persuaded
    1.09
     sworn
    1.09
     convinced
    1.09
     campaigning
    1.08
     obliged
    1.08
     embroiled
    1.08
    Activations Density 0.317%

    No Known Activations