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. 8-RES-JB
    6. 18113
    Prev
    Next
    INDEX
    Explanations

    phrases related to benefiting or gaining advantage

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to benefits or advantages gained from various situations or contexts

    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
    numbered
    -0.79
     proble
    -0.76
    pic
    -0.74
    apo
    -0.73
    \'
    -0.73
    channelAvailability
    -0.70
    isSpecialOrderable
    -0.69
    queue
    -0.68
    prep
    -0.68
    SCP
    -0.67
    POSITIVE LOGITS
     afar
    0.86
     owning
    0.83
     having
    0.81
     rescuing
    0.76
     maintaining
    0.76
     knowing
    0.75
     seeing
    0.75
     exploiting
    0.74
     adopting
    0.74
     globalization
    0.73
    Activations Density 0.069%

    No Known Activations