© 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. 11-RES-JB
    11. 21327
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery or equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms and features related to product specifications and design elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.86
    humans
    -0.81
    people
    -0.79
    puting
    -0.78
    genre
    -0.77
    ongo
    -0.77
    prison
    -0.76
    reason
    -0.75
    politics
    -0.74
    puters
    -0.73
    POSITIVE LOGITS
     adjustable
    1.41
     threaded
    1.34
     stainless
    1.34
     removable
    1.30
     Stainless
    1.21
     drilled
    1.21
     molded
    1.17
     insulated
    1.16
     silicone
    1.15
     ceramic
    1.13
    Activations Density 0.257%

    No Known Activations