© 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. 7-RES-JB
    11. 17148
    Prev
    Next
    INDEX
    Explanations

    phrases related to imitation or following someone's actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "follow in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bucks
    -0.65
     Chargers
    -0.64
     Swordsman
    -0.62
     SPORTS
    -0.62
     Basics
    -0.61
     Feast
    -0.61
     Intermediate
    -0.59
     Sands
    -0.58
     Methods
    -0.57
    pedia
    -0.57
    POSITIVE LOGITS
    soType
    0.89
    alien
    0.78
    alpha
    0.77
    creat
    0.77
    same
    0.76
    relation
    0.74
    animate
    0.74
    abilities
    0.73
    ordinate
    0.73
    rodu
    0.72
    Activations Density 0.119%

    No Known Activations