© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    words related to technology and communication

    oai_token-act-pair · gpt-3.5-turbo

    positive descriptors and characteristics related to people or groups

    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
    colored
    -1.06
    avored
    -1.06
    defense
    -1.05
    --
    -1.04
    bors
    -1.00
    Defense
    -0.97
     canceled
    -0.90
    —-
    -0.89
    caliber
    -0.87
    centered
    -0.86
    POSITIVE LOGITS
     realise
    1.76
     organise
    1.66
     organising
    1.65
     maths
    1.65
     recognise
    1.65
     realised
    1.64
     colour
    1.60
     £
    1.60
     humour
    1.59
     recognised
    1.58
    Activations Density 1.626%

    No Known Activations