© 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. 20270
    Prev
    Next
    INDEX
    Explanations

    methods of transportation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to modes of transportation

    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
     Attributes
    -0.71
    natureconservancy
    -0.69
    ealous
    -0.68
     Marketable
    -0.67
     theolog
    -0.67
     McInt
    -0.66
     sculpt
    -0.64
     Painter
    -0.64
     Guth
    -0.64
    aceae
    -0.63
    POSITIVE LOGITS
     ferry
    1.48
     taxis
    1.43
     commuter
    1.39
     commute
    1.33
     taxi
    1.32
     subway
    1.29
     flights
    1.29
     transit
    1.28
     buses
    1.28
     courier
    1.27
    Activations Density 1.139%

    No Known Activations