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. 23530
    Prev
    Next
    INDEX
    Explanations

    adjectives related to minimalism or essential elements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being minimal or stripped down

    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
    anwhile
    -0.85
    abulary
    -0.76
    arios
    -0.74
     Democr
    -0.72
    oldown
    -0.71
    afort
    -0.70
    ickr
    -0.70
    agents
    -0.68
    å°Ĩ
    -0.68
    alez
    -0.67
    POSITIVE LOGITS
    footed
    1.17
    foot
    1.16
    bones
    1.08
    faced
    1.03
    feet
    0.99
    clad
    0.96
    handed
    0.94
     bare
    0.94
    teen
    0.93
    chest
    0.91
    Activations Density 0.014%

    No Known Activations