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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7510
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "beck" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ck" in words

    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
    DonaldTrump
    -0.74
     exha
    -0.72
    psons
    -0.64
     maj
    -0.63
     impending
    -0.61
     lockout
    -0.61
     Kot
    -0.59
     pestic
    -0.59
     unheard
    -0.58
     ILCS
    -0.58
    POSITIVE LOGITS
    erman
    1.24
    lace
    1.20
    enstein
    1.17
    ert
    1.08
    hoff
    1.08
    enberg
    1.07
    ham
    1.06
    enzie
    1.04
    enger
    1.03
    ley
    1.03
    Activations Density 0.026%

    No Known Activations