© 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. 6712
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional careers and achievements

    oai_token-act-pair · gpt-3.5-turbo

    commas in a document

    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
    =#
    -0.77
    urry
    -0.73
    "]=>
    -0.71
    abus
    -0.68
    geist
    -0.67
    imize
    -0.66
    chin
    -0.65
    ards
    -0.64
    oner
    -0.64
    awks
    -0.64
    POSITIVE LOGITS
     earning
    1.17
     joining
    1.08
     preferring
    1.08
     becoming
    1.08
     appearing
    1.07
     graduating
    1.06
     donating
    1.05
     specializing
    1.05
     overseeing
    1.04
     befriend
    1.04
    Activations Density 0.300%

    No Known Activations