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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10194
    Prev
    Next
    INDEX
    Explanations

    phrases related to purpose or intention, often involving comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    infinitive phrases involving "to" followed by a verb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crom
    -0.66
    iked
    -0.66
     Halls
    -0.64
     Corpus
    -0.64
     Centauri
    -0.63
     OK
    -0.63
    âĿ
    -0.63
     Gram
    -0.62
     Nile
    -0.61
    istries
    -0.60
    POSITIVE LOGITS
     minimize
    1.00
     imply
    0.97
     recreate
    0.93
     exclude
    0.93
     reassure
    0.91
     deprive
    0.90
     eliminate
    0.90
     remind
    0.89
     preclude
    0.89
     emulate
    0.89
    Activations Density 0.043%

    No Known Activations