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. 11-RES-JB
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    phrases related to attributing responsibility or blame

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blame and responsibility, particularly using variations of the word "lay."

    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
    ively
    -0.79
    qua
    -0.67
     [+
    -0.63
    ãĥ¯
    -0.63
    iles
    -0.61
     pandemonium
    -0.61
    Ther
    -0.60
    ruciating
    -0.59
     Enh
    -0.59
     Applied
    -0.58
    POSITIVE LOGITS
     groundwork
    1.23
     claim
    1.11
     siege
    1.01
     bare
    1.01
     dormant
    0.99
     waste
    0.96
     blame
    0.87
     foundations
    0.82
     down
    0.81
    ering
    0.81
    Activations Density 0.037%

    No Known Activations