© 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. 8-RES-JB
    11. 7752
    Prev
    Next
    INDEX
    Explanations

    proper nouns or terms starting with 'N'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character sequence "N 1"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gibraltar
    -0.66
     unsupported
    -0.65
     Vaj
    -0.65
     diplom
    -0.65
     Cerberus
    -0.64
    espie
    -0.63
     surve
    -0.63
     hypot
    -0.62
     Sparrow
    -0.62
     Izan
    -0.61
    POSITIVE LOGITS
    onsense
    1.30
    ucle
    1.26
    aughty
    1.24
    ihil
    1.18
    usra
    1.15
    ectar
    1.13
    ymph
    1.12
    umeric
    1.11
    intend
    1.09
    umbered
    1.09
    Activations Density 0.036%

    No Known Activations