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. 23356
    Prev
    Next
    INDEX
    Explanations

    instances where people or groups come together for a common purpose or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize collective actions and collaboration

    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
    士
    -0.69
     viol
    -0.68
    availability
    -0.63
    condition
    -0.62
    ror
    -0.61
    tank
    -0.60
    wash
    -0.58
    yright
    -0.58
    taker
    -0.58
    76561
    -0.56
    POSITIVE LOGITS
     Together
    0.87
     disparate
    0.83
    itud
    0.77
    together
    0.77
     dots
    0.76
    yss
    0.75
    女
    0.74
     together
    0.73
    ãĤ¤ãĥĪ
    0.73
    Together
    0.68
    Activations Density 0.375%

    No Known Activations