© 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. 9-RES-JB
    11. 16284
    Prev
    Next
    INDEX
    Explanations

    the word "full" followed by various contexts described in the provided text snippets

    oai_token-act-pair · gpt-3.5-turbo

    the concept of comprehensiveness or completeness in various contexts

    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
    hots
    -0.81
    Tickets
    -0.71
     Slowly
    -0.68
    rosso
    -0.68
    rus
    -0.67
    particularly
    -0.66
    lished
    -0.66
     newsletters
    -0.66
    cially
    -0.66
    reetings
    -0.66
    POSITIVE LOGITS
     extent
    1.42
     brunt
    1.17
     breadth
    1.12
     spectrum
    1.11
     amount
    1.07
     complement
    1.05
     scope
    1.04
     range
    1.00
     array
    0.95
     ensemble
    0.95
    Activations Density 0.104%

    No Known Activations