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. 8-RES-JB
    6. 57
    Prev
    Next
    INDEX
    Explanations

    statements or assertions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the fact that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.77
    Si
    -0.72
    pec
    -0.70
    vc
    -0.69
    uttering
    -0.66
    ocking
    -0.64
    yn
    -0.64
    ately
    -0.63
    Eye
    -0.63
    wn
    -0.63
    POSITIVE LOGITS
     someone
    0.96
     they
    0.94
     nobody
    0.87
     there
    0.84
     somebody
    0.84
     hindsight
    0.83
     we
    0.81
     everyone
    0.79
     anyone
    0.76
     humans
    0.76
    Activations Density 0.084%

    No Known Activations