© 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. 8-RES-JB
    11. 18736
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or specific places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "in" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0000000000000000
    -0.80
    wcsstore
    -0.73
    CV
    -0.70
    trump
    -0.69
     istg
    -0.68
    ERROR
    -0.67
    iris
    -0.66
     onstage
    -0.66
    Iterator
    -0.66
    timer
    -0.64
    POSITIVE LOGITS
    effic
    1.22
     Europe
    1.21
     Germany
    1.14
    efficiency
    1.11
     France
    1.10
    roads
    1.10
     Britain
    1.09
     America
    1.08
    humane
    1.07
     accordance
    1.06
    Activations Density 0.366%

    No Known Activations