© 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. 11716
    Prev
    Next
    INDEX
    Explanations

    keywords related to setting up configurations and commands in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "set" and its variations in context, particularly in programming or configuration settings

    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
    Ò
    -0.67
    sylvania
    -0.67
    PH
    -0.67
    issance
    -0.66
    past
    -0.65
     Schwe
    -0.64
    isks
    -0.63
    sbm
    -0.62
    ä¼
    -0.61
    ç«
    -0.61
    POSITIVE LOGITS
    tle
    1.09
    uid
    0.95
    ter
    0.93
    Timeout
    0.87
    tering
    0.85
    ters
    0.84
     forth
    0.83
    env
    0.81
    upt
    0.77
    default
    0.76
    Activations Density 0.040%

    No Known Activations