© 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. 10-RES-JB
    11. 9951
    Prev
    Next
    INDEX
    Explanations

    phrases where the concept of "sameness" or similarity is emphasized

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express similarity or equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WI
    -0.73
    rollers
    -0.72
    Ķ
    -0.71
    rection
    -0.70
    orts
    -0.69
    ronics
    -0.69
    arest
    -0.68
    rosso
    -0.68
    rique
    -0.67
    xtap
    -0.67
    POSITIVE LOGITS
     thing
    1.29
     way
    1.00
     exact
    0.89
     amount
    0.88
     size
    0.86
     kind
    0.85
     extent
    0.81
     anymore
    0.81
     regardless
    0.81
     sort
    0.80
    Activations Density 0.045%

    No Known Activations