© 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. 4-RES-JB
    11. 14832
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    historical dates and references related to ancient civilizations

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

    No Comments

    Negative Logits
    cipled
    -0.81
    iott
    -0.76
    Consumer
    -0.75
     Tonight
    -0.74
    NESS
    -0.73
     Ally
    -0.72
    burse
    -0.71
     Comcast
    -0.71
    wage
    -0.70
     Blaster
    -0.69
    POSITIVE LOGITS
     Archae
    1.16
     Egyptians
    1.16
    Ancient
    1.13
     ancestor
    1.12
     archae
    1.09
     archaeological
    1.06
     civilizations
    1.06
     civilisation
    1.05
     Ethiop
    1.03
     Romans
    1.03
    Activations Density 0.852%

    No Known Activations