© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17146
    Prev
    Next
    INDEX
    Explanations

    phrases related to distribution or scattering

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scattered" and its variations, indicating a focus on distribution or dispersion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sen
    -0.75
    asus
    -0.74
    ests
    -0.70
    Fight
    -0.68
    Demand
    -0.65
    Trade
    -0.64
    resses
    -0.63
    acts
    -0.63
     Obesity
    -0.62
    uberty
    -0.62
    POSITIVE LOGITS
     scattered
    1.07
     dispersed
    0.84
     scattering
    0.83
     scatter
    0.79
     bom
    0.78
     across
    0.77
     littered
    0.77
     sprinkled
    0.77
    llor
    0.75
    sheets
    0.75
    Activations Density 0.075%

    No Known Activations