© 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. 681
    Prev
    Next
    INDEX
    Explanations

    individual words starting with the letter 'u'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'u'

    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
     Scarlet
    -0.65
     executions
    -0.62
     rendition
    -0.61
     Sparrow
    -0.59
     Sins
    -0.58
     Alice
    -0.58
     Emin
    -0.56
     Opportun
    -0.56
     Apostles
    -0.56
     loyalty
    -0.55
    POSITIVE LOGITS
    pperc
    1.62
    mpire
    1.41
    reth
    1.30
    ppers
    1.29
    pped
    1.24
    rolog
    1.20
    pping
    1.14
    seless
    1.13
    zbek
    1.13
    mp
    1.12
    Activations Density 0.016%

    No Known Activations