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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15008
    Prev
    Next
    INDEX
    Explanations

    instances of the word "established" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being well-established or recognized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hner
    -0.73
     Marketable
    -0.71
    ã
    -0.68
    govtrack
    -0.67
    Crystal
    -0.67
    sol
    -0.66
    plet
    -0.64
    ioxide
    -0.64
    quel
    -0.64
    mith
    -0.63
    POSITIVE LOGITS
    lishes
    1.05
    established
    0.88
     establishes
    0.85
    ablished
    0.83
    iates
    0.79
     friendships
    0.79
     established
    0.79
     partnerships
    0.77
    ties
    0.76
     relationships
    0.76
    Activations Density 0.015%

    No Known Activations