© 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. 11-RES-JB
    11. 2473
    Prev
    Next
    INDEX
    Explanations

    phrases related to high costs or things being overpriced

    oai_token-act-pair · gpt-3.5-turbo

    references to costs and high prices

    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
    oral
    -0.68
    indal
    -0.67
     Virus
    -0.66
    english
    -0.64
     Brief
    -0.62
    disabled
    -0.61
     Activ
    -0.60
    apons
    -0.60
    Introduced
    -0.60
    OLOG
    -0.60
    POSITIVE LOGITS
     prohib
    1.55
     astronomical
    1.42
     astron
    1.27
     inflated
    1.26
     peanuts
    1.23
     hefty
    1.13
     extortion
    1.08
     steep
    1.08
     unsustainable
    1.07
     unaff
    1.05
    Activations Density 0.265%

    No Known Activations