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. 18520
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the color red

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or entities

    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
    ann
    -0.75
    acs
    -0.74
     Ic
    -0.73
    nai
    -0.70
    Ni
    -0.69
    Kay
    -0.68
    ancy
    -0.67
    annon
    -0.67
     Akin
    -0.65
    essions
    -0.65
    POSITIVE LOGITS
     Red
    2.60
    Red
    2.46
     red
    2.24
     RED
    2.21
    red
    2.08
    RED
    2.08
    Redd
    2.04
     Yellow
    1.49
     crimson
    1.40
     Reds
    1.36
    Activations Density 0.142%

    No Known Activations