© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17736
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that start with the letter N

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific identifier or notation, likely linked to characters or elements within a narrative or category

    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
     Izan
    -0.64
     Vaj
    -0.62
     Cerberus
    -0.62
     Rebels
    -0.61
     tem
    -0.60
     Gibraltar
    -0.60
     Sparrow
    -0.60
    espie
    -0.60
     hypot
    -0.59
     diplom
    -0.59
    POSITIVE LOGITS
    onsense
    1.31
    aughty
    1.29
    ucle
    1.24
    ihil
    1.21
    ymph
    1.19
    umbered
    1.15
    ectar
    1.14
    ighth
    1.13
    usra
    1.13
    autical
    1.12
    Activations Density 0.040%

    No Known Activations