© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 494
    Prev
    Next
    INDEX
    Explanations

    phrases related to combinations or mixtures of different elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combination" in various contexts

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

    No Comments

    Negative Logits
    yers
    -0.83
    selves
    -0.80
    artisan
    -0.71
    zbollah
    -0.71
    gor
    -0.70
     Coffin
    -0.67
    iak
    -0.66
     Passage
    -0.66
    ĺħ
    -0.66
    criptions
    -0.66
    POSITIVE LOGITS
     combinations
    0.74
     thereof
    0.72
     seamlessly
    0.72
     combination
    0.71
     combines
    0.70
    ilde
    0.68
    ALLY
    0.66
    ively
    0.66
     between
    0.64
     accelerator
    0.64
    Activations Density 0.019%

    No Known Activations