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. 20671
    Prev
    Next
    INDEX
    Explanations

    pronouns or references to people other than the speaker

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective experience of others

    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
    omorph
    -0.73
    forestation
    -0.69
    tein
    -0.68
    Accessory
    -0.64
    orno
    -0.63
    nec
    -0.63
    BTC
    -0.61
    osterone
    -0.61
    height
    -0.60
    Runner
    -0.60
    POSITIVE LOGITS
     describ
    0.83
     besides
    0.76
     afforded
    0.75
     else
    0.75
     behaved
    0.74
    Joined
    0.73
     succumbed
    0.71
     includ
    0.71
     who
    0.71
     subjected
    0.70
    Activations Density 0.014%

    No Known Activations