© 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. 23436
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or origin of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "everything" or "it all."

    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
    gee
    -0.76
     Gors
    -0.69
    raviolet
    -0.65
    yip
    -0.64
     Parables
    -0.62
    ctors
    -0.60
     critic
    -0.60
    riad
    -0.59
     Press
    -0.59
     Advocate
    -0.59
    POSITIVE LOGITS
    ocation
    1.10
    ocating
    1.00
    udes
    0.98
    together
    0.93
    ocated
    0.93
    oys
    0.86
    ocations
    0.86
    iances
    0.86
    ayed
    0.85
    ocative
    0.85
    Activations Density 0.038%

    No Known Activations