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. 0-RES-JB
    6. 10655
    Prev
    Next
    INDEX
    Explanations

    words related to physical or metaphorical damage

    oai_token-act-pair · gpt-3.5-turbo

    references to physical or financial damage

    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
    tern
    -0.74
    aucuses
    -0.69
    ublic
    -0.69
    maid
    -0.69
    meet
    -0.68
    VIEW
    -0.67
    gin
    -0.65
     Caf
    -0.64
     Selected
    -0.64
    ango
    -0.64
    POSITIVE LOGITS
     damage
    3.56
    damage
    2.61
     Damage
    2.55
    Damage
    2.31
     damages
    2.29
     harm
    1.92
     damaging
    1.83
     damaged
    1.83
     dmg
    1.79
     havoc
    1.71
    Activations Density 0.021%

    No Known Activations