© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific places or people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'o' in various contexts

    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
     glim
    -0.92
     condem
    -0.78
     confir
    -0.70
    t
    -0.69
     cryst
    -0.67
    rified
    -0.66
    mble
    -0.65
    s
    -0.65
     Seym
    -0.65
    è£
    -0.64
    POSITIVE LOGITS
    zzi
    1.44
    cean
    1.18
    zzo
    1.15
    ctor
    1.05
    cephal
    1.04
    oms
    1.03
    onga
    1.00
    ebus
    0.97
    vernment
    0.94
    zza
    0.94
    Activations Density 0.077%

    No Known Activations