© 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. 1-RES-JB
    11. 16453
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to interactions or intersections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "inter-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.71
    ORK
    -0.68
     tremend
    -0.65
    EStream
    -0.65
     Kraken
    -0.64
     deeds
    -0.61
     bras
    -0.61
     Skydragon
    -0.60
     Hearts
    -0.59
    avorite
    -0.58
    POSITIVE LOGITS
    inter
    0.96
    mediate
    0.94
    continental
    0.82
    ventions
    0.81
    active
    0.80
    stice
    0.80
    medi
    0.80
    ception
    0.76
    pret
    0.76
    vention
    0.75
    Activations Density 0.003%

    No Known Activations