© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23916
    Prev
    Next
    INDEX
    Explanations

    specific physical attributes or characteristics related to tools or equipment

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of suitability and performance for various tasks or applications

    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
     Vote
    -0.70
    redit
    -0.69
    oiler
    -0.67
    qi
    -0.65
    appointed
    -0.64
    Vote
    -0.64
    DragonMagazine
    -0.64
    Trust
    -0.63
    ————
    -0.62
    ledge
    -0.62
    POSITIVE LOGITS
     situations
    1.67
     applications
    1.51
     setups
    1.42
     environments
    1.39
     scenarios
    1.36
     occasions
    1.33
     contexts
    1.28
     tasks
    1.26
     purposes
    1.22
     workload
    1.20
    Activations Density 0.444%

    No Known Activations