© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 968
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or situations that are challenging or require effort

    oai_token-act-pair · gpt-3.5-turbo

    terms related to difficulty and challenges

    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
    vine
    -0.74
    illance
    -0.70
     references
    -0.67
    notations
    -0.64
    bris
    -0.60
    Charges
    -0.59
    strong
    -0.58
    ablishment
    -0.57
    ãĥĥãĥī
    -0.57
    gdala
    -0.57
    POSITIVE LOGITS
     task
    1.00
     tasks
    0.93
     feat
    0.83
    icult
    0.79
    task
    0.78
     chores
    0.77
     terrain
    0.76
    pmwiki
    0.75
     administr
    0.74
     chore
    0.74
    Activations Density 0.079%

    No Known Activations