© 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. 10-RES-JB
    11. 17510
    Prev
    Next
    INDEX
    Explanations

    phrases related to a temporary duration or status

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related concepts and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reloaded
    -0.78
    agonist
    -0.75
     Authent
    -0.72
    alis
    -0.70
     Mahjong
    -0.67
    ards
    -0.67
    dale
    -0.66
    enburg
    -0.65
    ourt
    -0.64
    rosis
    -0.64
    POSITIVE LOGITS
    frames
    1.21
     elapsed
    1.20
     frame
    1.14
     allotted
    1.13
    frame
    1.05
     spent
    1.05
     horizon
    1.01
     continuum
    0.98
     constraints
    0.98
     periods
    0.97
    Activations Density 0.058%

    No Known Activations