© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 2855
    Prev
    Next
    INDEX
    Explanations

    time-related terms or phrases, particularly focusing on 'all-time'

    oai_token-act-pair · gpt-3.5-turbo

    phrases mentioning "all-time highs" related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pherd
    -0.79
    uri
    -0.72
    endas
    -0.72
    »Ĵ
    -0.72
    agra
    -0.72
     caucuses
    -0.69
    ĪĴ
    -0.63
    haar
    -0.63
    awaru
    -0.63
    ropri
    -0.62
    POSITIVE LOGITS
     Ago
    0.68
     highs
    0.67
    parable
    0.67
    theless
    0.66
    listed
    0.66
     Greatest
    0.65
     msec
    0.64
     lows
    0.64
     favourite
    0.64
     record
    0.63
    Activations Density 0.024%

    No Known Activations