© 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. 6-RES-JB
    11. 936
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by locations or timeframes

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" indicating source or origin in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faced
    -0.87
    aqu
    -0.80
    ridges
    -0.78
    aca
    -0.70
    important
    -0.68
    hyde
    -0.66
    certain
    -0.65
    proof
    -0.65
    Guide
    -0.63
    zed
    -0.63
    POSITIVE LOGITS
     afar
    1.28
     whence
    1.00
     abroad
    0.88
     thence
    0.87
     scratch
    0.85
     inception
    0.82
     1973
    0.81
     1967
    0.78
     1951
    0.77
     1979
    0.76
    Activations Density 0.186%

    No Known Activations