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. 1-RES-JB
    6. 19967
    Prev
    Next
    INDEX
    Explanations

    words related to providing advice or consultation, especially in a professional context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advisors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eat
    -0.71
    buck
    -0.70
    brance
    -0.68
    days
    -0.67
    kay
    -0.66
    bered
    -0.66
    imb
    -0.66
    original
    -0.65
    ©¶æ¥µ
    -0.65
    ching
    -0.65
    POSITIVE LOGITS
     advisor
    1.43
     advisors
    1.14
     Advisor
    1.10
     adviser
    1.01
     counselor
    0.96
     Adviser
    0.93
     Advis
    0.88
     advising
    0.85
     counselors
    0.82
     mentor
    0.81
    Activations Density 0.011%

    No Known Activations