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. 19620
    Prev
    Next
    INDEX
    Explanations

    ranks or titles, especially military ranks like 'Colonel' and 'General'

    oai_token-act-pair · gpt-3.5-turbo

    titles and ranks associated with military personnel

    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
    âĹ¼
    -0.76
     renters
    -0.73
     Horses
    -0.71
    SourceFile
    -0.68
    Torrent
    -0.68
    Crash
    -0.68
    Sensor
    -0.65
    Score
    -0.65
    BRE
    -0.65
    âĶģ
    -0.64
    POSITIVE LOGITS
    anamo
    1.06
    dinand
    0.99
     Mattis
    0.93
     Gaddafi
    0.92
    utenant
    0.85
    andum
    0.85
     Eisenhower
    0.82
    apons
    0.82
     Marshal
    0.80
     stationed
    0.79
    Activations Density 0.041%

    No Known Activations