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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 15891
    Prev
    Next
    INDEX
    Explanations

    powerful or intense confrontational words and phrases related to fighting or struggle

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicts or struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mellon
    -0.80
    Arch
    -0.70
    Typ
    -0.70
    Reviewer
    -0.68
    Software
    -0.68
     Scotia
    -0.67
     Extensions
    -0.66
     satisf
    -0.66
    Apps
    -0.65
     Architects
    -0.63
    POSITIVE LOGITS
     fight
    3.58
    fight
    2.85
     fights
    2.63
     Fight
    2.49
     battle
    2.19
    Fight
    2.17
     FIGHT
    2.15
     brawl
    2.11
    fights
    2.06
     fought
    1.88
    Activations Density 0.021%

    No Known Activations