Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15852
    Prev
    Next
    INDEX
    Explanations

    time-related phrases with a focus on events or occurrences happening a specific number of years before or after a certain point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating temporal sequences or events that occur after a specific time reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.73
    hab
    -0.73
    ãĤĬ
    -0.73
    habi
    -0.72
    gallery
    -0.71
    tie
    -0.69
    zzo
    -0.68
    late
    -0.68
    uci
    -0.67
    Management
    -0.67
    POSITIVE LOGITS
     enactment
    0.98
     inception
    0.95
     launching
    0.88
     completion
    0.88
     announcing
    0.87
     graduating
    0.85
     launch
    0.84
     founding
    0.83
     debut
    0.81
     arrival
    0.81
    Activations Density 0.134%

    No Known Activations