© 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 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. 7-RES-JB
    11. 21246
    Prev
    Next
    INDEX
    Explanations

    dates written in the format "Month Year."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "In" followed by a number or date, indicating references to time or specific events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unemploy
    -0.73
     lodged
    -0.72
     endors
    -0.69
     behav
    -0.68
     outwe
    -0.67
     revoked
    -0.67
     nailed
    -0.66
     combatants
    -0.65
     ingred
    -0.65
     spoil
    -0.64
    POSITIVE LOGITS
    ventory
    1.44
    cluding
    1.39
    strument
    1.21
    visible
    1.21
    clude
    1.21
    cluded
    1.20
    juries
    1.19
    iti
    1.18
    spect
    1.18
     addition
    1.18
    Activations Density 0.150%

    No Known Activations