© 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. 3-RES-JB
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "recent" events or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lua
    -0.72
    anski
    -0.68
    isha
    -0.67
    abba
    -0.67
    aina
    -0.67
    gee
    -0.66
    vant
    -0.66
    umm
    -0.65
    matic
    -0.65
    Lyn
    -0.65
    POSITIVE LOGITS
     edition
    0.82
     incarnation
    0.82
     installment
    0.77
     iteration
    0.73
     (>
    0.72
    Published
    0.70
     manifestations
    0.69
     Occupations
    0.68
     episode
    0.68
     predecessors
    0.68
    Activations Density 0.015%

    No Known Activations