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. 3-RES-JB
    6. 14510
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to an indefinite group of people

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group of people, often in the context of societal issues or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eleven
    -0.86
    CCC
    -0.85
     Globe
    -0.69
    VW
    -0.67
     Club
    -0.67
     Unlimited
    -0.67
     Amen
    -0.67
    cgi
    -0.66
     Defence
    -0.65
    Bull
    -0.64
    POSITIVE LOGITS
    're
    1.28
    'd
    1.15
    'll
    1.14
    've
    1.11
     selves
    0.94
    selves
    0.89
    self
    0.88
     could
    0.85
     shouldn
    0.82
    zbollah
    0.79
    Activations Density 0.252%

    No Known Activations