© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10790
    Prev
    Next
    INDEX
    Explanations

    general concepts or patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to generalized concepts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scroll
    -0.73
    Diamond
    -0.72
    vana
    -0.72
    ILLE
    -0.72
     Tycoon
    -0.71
    Mini
    -0.67
    ÄŁ
    -0.66
    XL
    -0.66
    Sea
    -0.66
    rero
    -0.66
    POSITIVE LOGITS
    izations
    1.35
    ization
    1.17
    isations
    1.17
    izing
    1.11
    ities
    1.09
    izable
    1.08
    isation
    1.07
    ised
    1.06
     relativity
    1.05
    izes
    1.01
    Activations Density 0.029%

    No Known Activations