© 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. 9-RES-JB
    11. 2390
    Prev
    Next
    INDEX
    Explanations

    phrases related to commercial activities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and related phrases in the context of regulations or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lishes
    -0.74
    itol
    -0.74
    ilege
    -0.67
    oids
    -0.66
    atis
    -0.66
    ESE
    -0.65
    oleon
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
     Weekly
    -0.65
    stones
    -0.65
    POSITIVE LOGITS
    processing
    1.10
     grooming
    1.07
     photograp
    1.06
     drying
    1.06
     harvesting
    1.06
     sorting
    1.06
     processing
    1.02
     editing
    1.01
     fielding
    1.01
     distributing
    1.01
    Activations Density 0.283%

    No Known Activations