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. 22722
    Prev
    Next
    INDEX
    Explanations

    instances of ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'second' or 'second place'

    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
    mercial
    -0.71
    Ĥİ
    -0.54
    ateur
    -0.50
     sqor
    -0.50
    contract
    -0.50
    protein
    -0.49
    ateurs
    -0.48
    opol
    -0.48
    nit
    -0.48
    kinson
    -0.47
    POSITIVE LOGITS
    akra
    0.58
    ighty
    0.57
     explan
    0.56
    endment
    0.55
     {*
    0.55
    ipop
    0.54
    ciation
    0.54
     behav
    0.53
    aft
    0.52
    JV
    0.52
    Activations Density 1.732%

    No Known Activations