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. 9-RES-JB
    6. 13000
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes involving growth or change

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cycles, processes, and stages of development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audi
    -0.81
    VIDEO
    -0.74
    allowed
    -0.73
     microphone
    -0.72
    Fax
    -0.70
     taped
    -0.69
    password
    -0.68
     iT
    -0.68
     Fancy
    -0.68
    uggage
    -0.67
    POSITIVE LOGITS
     gradual
    1.36
     decay
    1.34
     cycles
    1.28
     attrition
    1.18
     accumulate
    1.14
     uphe
    1.13
     gradually
    1.12
     irreversible
    1.10
     transformations
    1.10
     transitions
    1.10
    Activations Density 0.968%

    No Known Activations