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. 19136
    Prev
    Next
    INDEX
    Explanations

    words related to mutation or altering of a physical nature

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mutate" and its variations, particularly in contexts related to harm or alteration

    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
     Defenders
    -0.96
    ¯¯
    -0.81
     Superior
    -0.69
    ulhu
    -0.68
    ħĭ
    -0.67
    LLOW
    -0.66
    ACP
    -0.66
     Concord
    -0.66
    ngth
    -0.66
     Franklin
    -0.65
    POSITIVE LOGITS
    iple
    1.14
    ually
    1.02
    atis
    0.93
    iously
    0.88
    iny
    0.88
    aroo
    0.84
    mut
    0.83
     mut
    0.83
    ivation
    0.83
    ual
    0.81
    Activations Density 0.006%

    No Known Activations