© 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. 24477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or initiation of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to beginning or starting processes or changes

    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
    ambling
    -0.67
    oche
    -0.58
    holding
    -0.58
    ju
    -0.57
     stopping
    -0.54
    gro
    -0.54
     intervening
    -0.54
    oppable
    -0.54
     originating
    -0.53
    ashington
    -0.52
    POSITIVE LOGITS
     to
    0.95
     anew
    0.79
     sqor
    0.67
     pains
    0.67
    heit
    0.63
     preparations
    0.61
     ta
    0.60
    §
    0.57
    imental
    0.57
     puberty
    0.57
    Activations Density 0.067%

    No Known Activations