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. 4-RES-JB
    6. 10050
    Prev
    Next
    INDEX
    Explanations

    mentions of events or actions happening at the sidelines

    oai_token-act-pair · gpt-3.5-turbo

    references to being on the sidelines

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

    No Comments

    Negative Logits
    eros
    -0.73
     descent
    -0.65
    imb
    -0.62
    gling
    -0.60
    ettel
    -0.60
    ryption
    -0.60
    ortion
    -0.59
    enos
    -0.59
    itars
    -0.59
    ator
    -0.58
    POSITIVE LOGITS
     sidelines
    1.13
     sideline
    0.83
    )</
    0.81
    itters
    0.78
    Ħ¢
    0.78
    swer
    0.71
    warm
    0.71
    bilt
    0.70
    sembly
    0.70
    tenance
    0.69
    Activations Density 0.009%

    No Known Activations