© 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. 7-RES-JB
    11. 23823
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to significant impactful events or actions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating significant actions or 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
     hump
    -0.70
     Gors
    -0.65
     Dome
    -0.62
     Meridian
    -0.57
     buys
    -0.56
    PI
    -0.55
     syndrome
    -0.55
     nig
    -0.55
     contracted
    -0.55
     Stur
    -0.54
    POSITIVE LOGITS
    Ĥİ
    0.92
    ¿½
    0.78
    eatures
    0.75
    ĺħ
    0.74
    ŃĶ
    0.73
    FML
    0.73
    ĸļ
    0.73
    ESCO
    0.72
    acters
    0.72
     partName
    0.70
    Activations Density 0.437%

    No Known Activations