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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20210
    Prev
    Next
    INDEX
    Explanations

    phrases related to company values and customer satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    statements about corporate missions and values focused on community and customer service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    might
    -0.73
    later
    -0.73
     guiActiveUn
    -0.70
    maybe
    -0.70
    NetMessage
    -0.69
     worse
    -0.68
     suddenly
    -0.68
    iots
    -0.65
     might
    -0.64
     snapped
    -0.64
    POSITIVE LOGITS
     strives
    1.24
    clus
    1.19
     strive
    1.16
     excellence
    1.08
    cellence
    1.07
     striving
    1.06
     ethos
    1.01
     motto
    1.00
     Principles
    0.99
     integrity
    0.97
    Activations Density 0.526%

    No Known Activations