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. 10745
    Prev
    Next
    INDEX
    Explanations

    the ordinal numbers 'fifth' and 'sixth' with varying degrees of importance

    oai_token-act-pair · gpt-3.5-turbo

    references to ordinal numbers, specifically "fifth" and "sixth."

    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
    BIL
    -0.76
    ++++++++++++++++
    -0.73
    VE
    -0.72
    ICO
    -0.72
    cks
    -0.71
    bda
    -0.71
    PRO
    -0.71
    facts
    -0.70
    EFF
    -0.69
    76561
    -0.69
    POSITIVE LOGITS
     inning
    1.18
    teenth
    0.91
    ieth
    0.89
    irty
    0.88
    umbnail
    0.86
    ousand
    0.85
     iteration
    0.85
    ority
    0.84
     century
    0.83
     installment
    0.82
    Activations Density 0.033%

    No Known Activations