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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17475
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collective decision-making or team action

    oai_token-act-pair · gpt-3.5-turbo

    references to collective experiences and teamwork

    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
    uates
    -0.65
    atory
    -0.65
     Eleven
    -0.61
    ftime
    -0.59
     Rash
    -0.59
     totality
    -0.59
    more
    -0.58
    CENT
    -0.58
    rx
    -0.57
    alky
    -0.56
    POSITIVE LOGITS
    've
    1.28
    'll
    1.20
    're
    1.18
    'd
    1.10
    athered
    1.00
    selves
    0.96
    ighed
    0.96
    asel
    0.91
    eding
    0.90
     encount
    0.89
    Activations Density 0.256%

    No Known Activations