© 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. 22596
    Prev
    Next
    INDEX
    Explanations

    references to behaviors or actions, often involving rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conduct or behavioral actions

    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
    cube
    -0.74
    corn
    -0.70
     msec
    -0.69
    username
    -0.64
     Fried
    -0.63
     Leopard
    -0.63
    aturated
    -0.62
    Lenin
    -0.60
    Kids
    -0.59
    Todd
    -0.59
    POSITIVE LOGITS
    ors
    1.10
    ivity
    1.06
    atform
    0.93
    uations
    0.92
    ional
    0.89
    ivities
    0.89
    ORS
    0.85
    ions
    0.83
    ively
    0.82
    ives
    0.82
    Activations Density 0.035%

    No Known Activations