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. 6-RES-JB
    6. 19021
    Prev
    Next
    INDEX
    Explanations

    instances where the subject is identified as present in the specified context

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and their variations

    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
     backdrop
    -0.75
     dictates
    -0.72
    reports
    -0.71
     Globe
    -0.65
     Cheong
    -0.65
     background
    -0.65
     highlights
    -0.64
     synopsis
    -0.62
     argues
    -0.61
     defines
    -0.60
    POSITIVE LOGITS
    misc
    0.73
    aterasu
    0.71
    ZI
    0.69
     kindred
    0.69
    nos
    0.67
     gonna
    0.66
    piracy
    0.66
     Oo
    0.66
    overe
    0.64
    quez
    0.64
    Activations Density 0.366%

    No Known Activations