Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16887
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs

    oai_token-act-pair · gpt-3.5-turbo

    negations and topics related to rules or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lov
    -0.91
     Leban
    -0.86
     Manz
    -0.83
    hl
    -0.83
     Kiw
    -0.83
     Hass
    -0.82
     Kir
    -0.81
     Kid
    -0.81
     Beir
    -0.79
     coh
    -0.79
    POSITIVE LOGITS
    atum
    1.00
    ativity
    0.99
    ato
    0.99
    ance
    0.93
    ACY
    0.92
    ata
    0.91
    atus
    0.87
    ure
    0.87
    utation
    0.85
    URE
    0.85
    Activations Density 0.232%

    No Known Activations