Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16246
    Prev
    Next
    INDEX
    Explanations

    references to specific names, likely proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate and candidates for positions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fisheries
    -0.71
     Torrent
    -0.68
     tamp
    -0.67
     Kod
    -0.65
     prick
    -0.64
     FCC
    -0.64
     centrif
    -0.64
     purse
    -0.64
     tune
    -0.64
     Monsanto
    -0.63
    POSITIVE LOGITS
    ties
    1.05
    gone
    1.01
    ocol
    1.01
    swick
    0.87
    orical
    0.85
    ãĤ¦ãĤ¹
    0.84
    rum
    0.84
    tm
    0.82
    umn
    0.82
    oops
    0.81
    Activations Density 0.036%

    No Known Activations