© 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. 4-RES-JB
    11. 14851
    Prev
    Next
    INDEX
    Explanations

    the phrase "At the same time."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at the same time."

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

    No Comments

    Negative Logits
    ussed
    -0.74
     purch
    -0.65
    olen
    -0.64
     drawer
    -0.64
    avorite
    -0.62
    reth
    -0.60
     um
    -0.60
     seller
    -0.59
     basement
    -0.59
     unequ
    -0.58
    POSITIVE LOGITS
    女
    0.84
    frames
    0.83
    aneously
    0.72
    rise
    0.71
    days
    0.71
    Roman
    0.67
     Constantin
    0.66
    bral
    0.65
    Trigger
    0.64
    uality
    0.64
    Activations Density 0.027%

    No Known Activations