© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 11205
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'ness', such as 'deservingness' and 'loneliness'

    oai_token-act-pair · gpt-3.5-turbo

    suffixes denoting states or qualities, particularly related to perception or characteristics of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zynski
    -0.78
    reon
    -0.73
    chnology
    -0.68
    odium
    -0.66
    vice
    -0.66
    inav
    -0.65
    ellar
    -0.64
    rament
    -0.63
    ompl
    -0.63
    nesium
    -0.60
    POSITIVE LOGITS
    iness
    1.22
    y
    0.90
    lessness
    0.89
    fulness
    0.87
    ness
    0.85
    iest
    0.85
    ï¸
    0.74
    iveness
    0.73
    istence
    0.72
    oft
    0.72
    Activations Density 0.062%

    No Known Activations