© 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. 24167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a purpose or function being fulfilled

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating functions or purposes of actions or items

    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
    pex
    -0.71
    patch
    -0.63
    acqu
    -0.61
    bis
    -0.61
    dp
    -0.61
    usted
    -0.61
    uesday
    -0.60
    clone
    -0.60
    opher
    -0.60
    ipl
    -0.60
    POSITIVE LOGITS
     as
    0.81
    umes
    0.73
     purposes
    0.68
     purpose
    0.64
    efully
    0.63
     primarily
    0.63
    ILY
    0.62
     audiences
    0.62
    umed
    0.61
     mainly
    0.61
    Activations Density 0.041%

    No Known Activations