© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 793
    Prev
    Next
    INDEX
    Explanations

    the word "Som" at various activations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Som" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovecraft
    -0.71
     upd
    -0.64
     recess
    -0.62
    UID
    -0.62
     uncomp
    -0.62
     compuls
    -0.62
     gallery
    -0.60
     Chargers
    -0.60
    ESS
    -0.58
     fiercely
    -0.57
    POSITIVE LOGITS
    eday
    1.62
    erville
    1.30
    alian
    1.19
    erton
    1.08
    mer
    1.07
    atic
    1.02
    asaki
    1.01
    amoto
    0.98
    atos
    0.98
    pson
    0.98
    Activations Density 0.029%

    No Known Activations