© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    patterns related to capability or capacity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capabilities or potential

    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
    isite
    -0.72
    famous
    -0.70
    scene
    -0.70
    era
    -0.70
    lass
    -0.67
     Bans
    -0.65
    lights
    -0.65
    cloth
    -0.64
    bane
    -0.64
    backer
    -0.64
    POSITIVE LOGITS
     withstand
    0.98
     inflicting
    0.94
     handling
    0.90
     delivering
    0.86
     achieving
    0.84
     reaching
    0.83
     sustaining
    0.82
     distinguishing
    0.82
     comprehend
    0.81
     generating
    0.80
    Activations Density 0.072%

    No Known Activations