© 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. 20044
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the continuous or ongoing nature of an action or state

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize continuity or a long-standing presence

    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
    edi
    -0.67
    regate
    -0.65
    uin
    -0.64
     Raise
    -0.63
     Rasm
    -0.61
     Inventory
    -0.61
    oto
    -0.61
    ————————————————
    -0.61
     wrap
    -0.60
    Days
    -0.59
    POSITIVE LOGITS
     able
    1.09
     regarded
    0.99
     considered
    0.85
     subjected
    0.83
     treated
    0.82
     relegated
    0.80
    acons
    0.79
     viewed
    0.78
    CLUD
    0.77
     credited
    0.76
    Activations Density 0.143%

    No Known Activations