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. 2-RES-JB
    6. 13154
    Prev
    Next
    INDEX
    Explanations

    words related to getting rid of specific objects, concepts, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "get rid of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.72
    enegger
    -0.69
     Fallon
    -0.64
     Immortal
    -0.63
    utton
    -0.63
     Loft
    -0.63
     Ung
    -0.61
    OPER
    -0.60
    KEN
    -0.59
    BE
    -0.58
    POSITIVE LOGITS
    itaire
    1.03
    anium
    0.90
    ings
    0.84
    ges
    0.81
    sheets
    0.81
    uations
    0.81
    osaurus
    0.80
    brush
    0.79
    cloth
    0.77
    ged
    0.76
    Activations Density 0.011%

    No Known Activations