© 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. 18469
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence, assistance, or declaration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    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
     reliance
    -0.74
     attributed
    -0.69
     resorted
    -0.68
     reliant
    -0.67
     fielded
    -0.62
     ancest
    -0.62
     synchronization
    -0.62
     Classification
    -0.60
     attributable
    -0.60
     exposures
    -0.59
    POSITIVE LOGITS
    brate
    0.92
     celebrate
    0.83
     stay
    0.83
    wark
    0.80
    orate
    0.79
    ivo
    0.77
    othe
    0.77
     uphold
    0.76
    attery
    0.76
    swer
    0.75
    Activations Density 0.119%

    No Known Activations