© 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. 6-RES-JB
    11. 14130
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action taken by a specific entity according to information provided

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.86
    eg
    -0.76
    estern
    -0.74
    ãĥĵ
    -0.68
     Subtle
    -0.67
    riage
    -0.66
    otin
    -0.66
    bers
    -0.63
    opard
    -0.62
    apore
    -0.62
    POSITIVE LOGITS
     sources
    0.88
    SOURCE
    0.75
     according
    0.73
    Rank
    0.72
     WS
    0.66
     citing
    0.65
    Sources
    0.62
     EW
    0.62
     Ops
    0.61
     Wass
    0.61
    Activations Density 0.043%

    No Known Activations