© 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. 23765
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or events involving physical movement

    oai_token-act-pair · gpt-3.5-turbo

    actions related to picking up or removing objects

    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
     favors
    -0.88
     Organizations
    -0.87
     someday
    -0.87
     centers
    -0.81
    waukee
    -0.79
     centralized
    -0.78
     honoring
    -0.78
     vacations
    -0.78
     nonprofits
    -0.77
     neighborhoods
    -0.77
    POSITIVE LOGITS
     apologised
    1.52
     apologise
    1.41
     manoeuv
    1.34
     realised
    1.32
     Whilst
    1.27
     CCTV
    1.27
     behaviour
    1.24
     organisers
    1.23
     tyres
    1.22
     tyre
    1.21
    Activations Density 0.400%

    No Known Activations