© 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. 16721
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring or keeping track of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases focusing on surveillance or monitoring

    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
    mes
    -0.70
    upon
    -0.69
    --------------------------------------------------------
    -0.68
     Archdemon
    -0.67
     allegations
    -0.66
    !/
    -0.66
    ------------------------
    -0.66
     directions
    -0.64
    ME
    -0.64
    çīĪ
    -0.64
    POSITIVE LOGITS
     sizeable
    0.93
     sizable
    0.91
     bunch
    0.90
     handful
    0.89
     secret
    0.85
     semblance
    0.84
    hold
    0.84
     lot
    0.83
     stash
    0.83
     foothold
    0.81
    Activations Density 0.142%

    No Known Activations