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. 11392
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical or religious concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to various "istic" concepts, indicating forms of classification or ideology

    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
    lain
    -0.91
    clips
    -0.83
    handle
    -0.78
    ãģ®éŃĶ
    -0.74
    agher
    -0.71
    BOOK
    -0.71
    handed
    -0.71
    ARDS
    -0.70
    ardless
    -0.68
    ortium
    -0.67
    POSITIVE LOGITS
     tendencies
    0.94
     persuasion
    0.74
    orically
    0.73
     endeavors
    0.72
    orical
    0.72
     optimism
    0.70
    ated
    0.69
     endeavour
    0.69
     outlook
    0.69
     asylum
    0.69
    Activations Density 0.029%

    No Known Activations