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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20275
    Prev
    Next
    INDEX
    Explanations

    words related to age groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific age groups

    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
     publication
    -0.77
     workflow
    -0.75
     interviewer
    -0.74
     editor
    -0.74
     standpoint
    -0.72
     organizer
    -0.70
     lender
    -0.69
     autobiography
    -0.68
     microphone
    -0.68
     educator
    -0.67
    POSITIVE LOGITS
    igers
    1.45
    ahs
    1.43
    itans
    1.38
    osaurs
    1.38
    gars
    1.37
    xes
    1.36
    angs
    1.35
    agers
    1.34
    rians
    1.34
    lems
    1.32
    Activations Density 0.622%

    No Known Activations