© 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. 3149
    Prev
    Next
    INDEX
    Explanations

    social media-related words and actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to biking activities

    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
    ãĥĥãĥī
    -0.90
    licted
    -0.67
    dimension
    -0.65
    shr
    -0.65
    İ
    -0.64
    enum
    -0.64
    shed
    -0.63
     ILCS
    -0.61
    Published
    -0.61
    mel
    -0.61
    POSITIVE LOGITS
    ikes
    1.42
    iking
    1.01
    lihood
    0.88
    iked
    0.85
    bike
    0.80
    hops
    0.79
    terday
    0.78
    peed
    0.75
    ike
    0.74
     biking
    0.73
    Activations Density 0.005%

    No Known Activations