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. 13063
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss the effects or impacts of various factors

    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
    REDACTED
    -0.75
    DragonMagazine
    -0.72
    ternity
    -0.71
    iguous
    -0.71
    OUP
    -0.69
     caveats
    -0.68
    netflix
    -0.68
    Rogue
    -0.67
    éĥ
    -0.66
    ÅŁ
    -0.65
    POSITIVE LOGITS
     psyche
    0.99
     livelihood
    0.93
     perception
    0.90
     credibility
    0.88
     morale
    0.84
     careers
    0.84
     perceptions
    0.83
     ability
    0.83
     competitiveness
    0.81
     downstream
    0.81
    Activations Density 0.419%

    No Known Activations