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. 20362
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "old"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "old."

    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
    utterstock
    -0.86
    Ĥİ
    -0.83
     athlet
    -0.78
    rawdownloadcloneembedreportprint
    -0.78
    rencies
    -0.77
    atography
    -0.76
    vous
    -0.74
    xtap
    -0.74
    ILA
    -0.74
    ONSORED
    -0.73
    POSITIVE LOGITS
     fashioned
    1.37
    rums
    0.97
    school
    0.95
    est
    0.91
    fashioned
    0.89
     standby
    0.85
     fart
    0.82
     school
    0.80
     timers
    0.79
    timer
    0.78
    Activations Density 0.039%

    No Known Activations