© 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. 15354
    Prev
    Next
    INDEX
    Explanations

    references to time sequences or durations

    oai_token-act-pair · gpt-3.5-turbo

    references to time or specific temporal markers

    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
    abad
    -0.65
    ijk
    -0.61
    ees
    -0.60
    Listener
    -0.58
     parity
    -0.58
    ello
    -0.58
     contention
    -0.58
    phabet
    -0.56
     alliances
    -0.56
     Paste
    -0.56
    POSITIVE LOGITS
    etheless
    0.75
    til
    0.69
    rily
    0.67
    fo
    0.66
    hered
    0.62
    thing
    0.60
    });
    0.59
     lacked
    0.59
     mattered
    0.59
    morning
    0.58
    Activations Density 0.598%

    No Known Activations