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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12155
    Prev
    Next
    INDEX
    Explanations

    verbs with the 'to' particle

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intent or purpose

    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
     Rapids
    -0.69
    cases
    -0.68
     Malf
    -0.67
    guards
    -0.67
     Maur
    -0.67
    parts
    -0.66
    points
    -0.66
    faces
    -0.65
    minus
    -0.64
    listed
    -0.62
    POSITIVE LOGITS
     emulate
    1.15
     capitalize
    1.08
     minimize
    1.06
     revive
    1.04
     recreate
    1.04
     imitate
    1.04
     maximize
    1.02
     promote
    1.02
     differentiate
    1.02
     preserve
    1.01
    Activations Density 0.165%

    No Known Activations