© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    the word "mostly" followed by a description or statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or prevalence

    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
    anth
    -0.86
    ylan
    -0.67
    atron
    -0.66
     Corruption
    -0.65
    emption
    -0.65
    uers
    -0.65
    ILE
    -0.63
     Ambassador
    -0.63
    ilion
    -0.62
     Orchestra
    -0.61
    POSITIVE LOGITS
     consisted
    0.83
     consist
    0.79
     overlooked
    0.78
     foc
    0.76
     consisting
    0.75
     cloudy
    0.75
     circumst
    0.74
     concentrated
    0.74
     concerned
    0.74
     ceremonial
    0.74
    Activations Density 0.044%

    No Known Activations