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. 8237
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or events related to personal or political narratives

    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
     guiActiveUnfocused
    -0.85
    yond
    -0.74
    arel
    -0.66
     antioxid
    -0.66
    eh
    -0.64
    istan
    -0.63
    Enlarge
    -0.63
    bie
    -0.63
    arry
    -0.62
    cedented
    -0.62
    POSITIVE LOGITS
     himself
    0.79
     herself
    0.63
    okia
    0.61
     passionately
    0.59
     tremend
    0.59
     instinctively
    0.59
    osaurus
    0.58
     extensively
    0.58
    idas
    0.58
     briefly
    0.58
    Activations Density 0.405%

    No Known Activations