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. 7931
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talk" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the act of discussing or communicating about various topics

    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
    emale
    -0.82
    rehens
    -0.73
    iverpool
    -0.73
    ascade
    -0.69
    eele
    -0.68
    ettel
    -0.67
    boa
    -0.67
    arte
    -0.66
    zyk
    -0.65
    iscal
    -0.63
    POSITIVE LOGITS
     Talk
    0.88
     about
    0.83
     loudly
    0.82
     aloud
    0.81
    bone
    0.80
     talk
    0.79
    Talk
    0.74
     louder
    0.74
    bag
    0.74
     frankly
    0.73
    Activations Density 0.041%

    No Known Activations