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. 10662
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to a specific person named "Sashi"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with the name "Takahashi."

    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
    sworth
    -0.89
    rified
    -0.79
    ship
    -0.71
    eering
    -0.69
    ilater
    -0.68
    course
    -0.67
    names
    -0.66
    paper
    -0.66
     Lazarus
    -0.66
    space
    -0.65
    POSITIVE LOGITS
    ya
    1.03
    Äĩ
    0.88
    pora
    0.88
    emi
    0.83
    á¹
    0.81
    ashi
    0.81
    ibi
    0.80
    imi
    0.79
    unta
    0.79
    iku
    0.78
    Activations Density 0.020%

    No Known Activations