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. 23297
    Prev
    Next
    INDEX
    Explanations

    names ending in 'bert'

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the name "Bert" in various contexts

    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
    esthetic
    -0.78
    heed
    -0.74
    ntil
    -0.72
    phis
    -0.70
    IFT
    -0.69
    olved
    -0.68
    istor
    -0.65
    oter
    -0.65
    stream
    -0.65
    phan
    -0.64
    POSITIVE LOGITS
    atoes
    0.86
    stadt
    0.79
     Hoover
    0.78
     Ames
    0.76
     Blumenthal
    0.75
    stown
    0.73
    rics
    0.73
    sson
    0.72
    furt
    0.71
    aum
    0.70
    Activations Density 0.019%

    No Known Activations