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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 3949
    Prev
    Next
    INDEX
    Explanations

    phrases related to mentoring

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to mentoring and mentorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.76
    jriwal
    -0.63
    Dim
    -0.61
     guessing
    -0.59
     Convention
    -0.57
     superf
    -0.57
     unavoidable
    -0.56
    foundland
    -0.56
     WATCHED
    -0.55
     belly
    -0.55
    POSITIVE LOGITS
    orship
    1.08
     mentors
    1.00
     mentor
    0.95
     Ment
    0.93
     ment
    0.91
    iors
    0.90
    lasses
    0.88
    hesis
    0.86
     tut
    0.84
    oring
    0.84
    Activations Density 0.041%

    No Known Activations