© 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. 9-RES-JB
    11. 18446
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe the prominence or notable characteristics of something

    oai_token-act-pair · gpt-3.5-turbo

    emphasized adjectives or descriptions that denote notable features or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORTS
    -0.85
    renheit
    -0.78
    ruary
    -0.74
    ople
    -0.74
    States
    -0.74
    ceans
    -0.70
    anners
    -0.66
    ULTS
    -0.66
    PATH
    -0.65
    aval
    -0.65
    POSITIVE LOGITS
     aspect
    1.52
     thing
    1.45
     pecul
    1.19
     feature
    1.18
     facet
    1.17
     part
    1.11
     factor
    1.10
     consequence
    1.06
     element
    1.06
     takeaway
    1.05
    Activations Density 0.173%

    No Known Activations