© 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. 4-RES-JB
    11. 15871
    Prev
    Next
    INDEX
    Explanations

    adjectives related to being factual, institutional, or related to physical measures

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the suffix "ional"

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

    No Comments

    Negative Logits
    tower
    -0.85
    KO
    -0.75
    Blog
    -0.72
    âĸĪâĸĪâĸĪâĸĪ
    -0.71
    ARDS
    -0.68
     Primal
    -0.68
    KEN
    -0.67
    conom
    -0.66
     Karl
    -0.65
     Coinbase
    -0.65
    POSITIVE LOGITS
    ities
    1.27
    ism
    1.23
    ized
    1.19
    ization
    1.10
    ised
    1.08
    ists
    1.03
    isations
    1.02
    idad
    1.01
    izational
    1.01
    isation
    0.99
    Activations Density 0.028%

    No Known Activations