© 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. 18536
    Prev
    Next
    INDEX
    Explanations

    phrases related to trends and fluctuations over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to trends and patterns in data

    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
     Honest
    -0.72
     Clever
    -0.69
     Choose
    -0.68
     CCTV
    -0.66
    quartered
    -0.65
     Loaded
    -0.65
     Ingredients
    -0.64
     Donation
    -0.64
     voic
    -0.64
    umbn
    -0.62
    POSITIVE LOGITS
     plateau
    1.49
     peaks
    1.35
     peaked
    1.31
     lows
    1.27
     downward
    1.20
     stagnation
    1.20
     dips
    1.15
     declines
    1.15
     downwards
    1.13
     decreasing
    1.10
    Activations Density 0.500%

    No Known Activations