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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11662
    Prev
    Next
    INDEX
    Explanations

    time-related phrases denoted by the prefix "mid-"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific time period within the day, particularly related to "mid-morning" or a similar time frame

    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
     Freed
    -0.75
     DRAG
    -0.74
     Ally
    -0.67
     Torch
    -0.67
     buffs
    -0.65
     merits
    -0.65
     badges
    -0.63
     Holding
    -0.62
     Achievements
    -0.62
     Canaver
    -0.61
    POSITIVE LOGITS
    century
    1.30
    sent
    1.29
    range
    1.27
    sized
    1.23
    season
    1.21
    tier
    1.20
    level
    1.18
    Atlantic
    1.17
    term
    1.16
    morning
    1.16
    Activations Density 0.022%

    No Known Activations