© 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. 18761
    Prev
    Next
    INDEX
    Explanations

    information about specific substances and their properties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the properties and effects of materials, particularly in relation to food and health

    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
     Franch
    -0.75
    ticket
    -0.70
    nn
    -0.68
     Camer
    -0.68
    cember
    -0.67
    nesday
    -0.66
    dt
    -0.66
     Caption
    -0.65
    ettel
    -0.65
    rame
    -0.65
    POSITIVE LOGITS
     properties
    1.28
     usefulness
    1.22
     medicinal
    1.21
     advantages
    1.20
     efficacy
    1.16
     potency
    1.12
     antib
    1.11
     versatility
    1.11
     qualities
    1.07
     therapeutic
    1.06
    Activations Density 0.238%

    No Known Activations