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. 18488
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or consistencies

    oai_token-act-pair · gpt-3.5-turbo

    the word "consistently" and similar phrases indicating reliability or frequency

    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
    ster
    -0.82
    sters
    -0.74
     Mour
    -0.67
    soc
    -0.67
    eral
    -0.65
    tein
    -0.64
    OTOS
    -0.63
    ja
    -0.62
    wife
    -0.62
     Jac
    -0.62
    POSITIVE LOGITS
    ãĤ©
    0.81
     outper
    0.81
     worshipped
    0.77
     conclud
    0.76
     rated
    0.75
     underestimated
    0.75
     impressed
    0.73
     maintained
    0.72
    nces
    0.71
     evolve
    0.71
    Activations Density 0.024%

    No Known Activations