© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23984
    Prev
    Next
    INDEX
    Explanations

    phrases related to sources or origins of information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.81
    otin
    -0.73
    eg
    -0.73
    riage
    -0.72
    76561
    -0.66
    estern
    -0.65
     Subtle
    -0.64
    affe
    -0.64
    ÃĥÃĤ
    -0.64
    cair
    -0.64
    POSITIVE LOGITS
     sources
    0.93
    SOURCE
    0.76
     according
    0.70
     WS
    0.69
    Sources
    0.66
     EW
    0.65
    Rank
    0.64
     Reuters
    0.63
     Ops
    0.60
     WP
    0.60
    Activations Density 0.046%

    No Known Activations