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. 11169
    Prev
    Next
    INDEX
    Explanations

    references to science fiction themes or elements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Planet" and its associations in a context

    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
    OUT
    -0.76
    ilant
    -0.75
    rown
    -0.74
    ugh
    -0.73
    displayText
    -0.73
    shire
    -0.72
    ãģĦ
    -0.72
    thens
    -0.71
    initions
    -0.71
    Interstitial
    -0.69
    POSITIVE LOGITS
    eers
    1.02
    arium
    0.99
     Parenthood
    0.98
     Planet
    0.92
     Pharma
    0.91
     Fitness
    0.89
    ciating
    0.85
     Eater
    0.83
     Hulk
    0.82
     Stronghold
    0.81
    Activations Density 0.020%

    No Known Activations