Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12773
    Prev
    Next
    INDEX
    Explanations

    description of financial costs or prices

    oai_token-act-pair · gpt-3.5-turbo

    references to requirements and costs associated with a product or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grave
    -0.79
     Nightmares
    -0.69
    911
    -0.69
    itus
    -0.68
    stre
    -0.67
     missed
    -0.64
    erguson
    -0.64
     reass
    -0.64
     ignored
    -0.63
    Interstitial
    -0.62
    POSITIVE LOGITS
    redients
    0.82
    expensive
    0.81
     (~
    0.81
    iameter
    0.77
    LV
    0.73
     (£
    0.72
     ($
    0.72
    Requirements
    0.72
    Installation
    0.72
     install
    0.71
    Activations Density 0.851%

    No Known Activations