© 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. 9-RES-JB
    11. 18641
    Prev
    Next
    INDEX
    Explanations

    numeric phrases mentioning 'two and a half'

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to durations or periods of time measured in "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.76
    ffen
    -0.72
    activity
    -0.72
    ãĥ¤
    -0.71
    Trend
    -0.71
    recy
    -0.70
    Hop
    -0.69
    ãĥ¯ãĥ³
    -0.69
    hester
    -0.69
    ãĤ¨ãĥ«
    -0.65
    POSITIVE LOGITS
     dozen
    1.08
     million
    1.03
     hour
    0.91
     thousand
    0.90
     century
    0.87
     billion
    0.87
    ousand
    0.87
    dozen
    0.83
     times
    0.82
    million
    0.81
    Activations Density 0.020%

    No Known Activations