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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 16126
    Prev
    Next
    INDEX
    Explanations

    words related to actions of undermining or discrediting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attempts to weaken or sabotage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lov
    -0.71
    area
    -0.67
    ather
    -0.66
    andro
    -0.65
    Spoiler
    -0.63
    cise
    -0.63
    ////////
    -0.62
    onna
    -0.62
    çĦ
    -0.61
    flo
    -0.60
    POSITIVE LOGITS
     havoc
    0.83
     perceptions
    0.76
     expectations
    0.73
     undermin
    0.73
     morale
    0.72
     livelihood
    0.70
     undermining
    0.68
     attempts
    0.67
    ments
    0.67
     deterrence
    0.67
    Activations Density 0.045%

    No Known Activations