© 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. 14048
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities and proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing conditionality and comparisons

    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
     INCLUD
    -0.64
    idon
    -0.62
     ALWAYS
    -0.62
    ãĤº
    -0.58
    ame
    -0.58
     conflic
    -0.57
    ESE
    -0.57
     havoc
    -0.55
     MUST
    -0.55
    ãĥī
    -0.54
    POSITIVE LOGITS
     marginally
    1.10
     briefly
    1.09
     occasional
    1.03
     spor
    0.98
     peripher
    0.97
     handful
    0.96
     modest
    0.95
     minor
    0.94
     rudimentary
    0.93
     sporadic
    0.93
    Activations Density 0.291%

    No Known Activations