© 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. 10-RES-JB
    11. 16342
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to traveling and journeys

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NPR
    -0.71
    acea
    -0.69
     forthcoming
    -0.61
    Sit
    -0.59
    Os
    -0.58
    Prop
    -0.58
    ©
    -0.58
    Dat
    -0.57
    ãĤ¶
    -0.57
    operator
    -0.57
    POSITIVE LOGITS
     undet
    1.17
     unnoticed
    1.09
     effortlessly
    1.03
     smoothly
    0.97
     sidx
    0.97
     seamlessly
    0.94
     pretending
    0.88
     unsc
    0.88
     corridors
    0.85
     searching
    0.85
    Activations Density 0.374%

    No Known Activations