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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5-RES-JB
    6. 309
    Prev
    Next
    INDEX
    Explanations

    phrases related to defiance or opposition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to refusal and attempts to enforce or acknowledge various actions or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certific
    -0.68
    igmatic
    -0.62
     GOODMAN
    -0.61
    MpServer
    -0.60
    rella
    -0.59
    versely
    -0.59
    opers
    -0.58
     Excel
    -0.57
    inately
    -0.57
     Surv
    -0.57
    POSITIVE LOGITS
    ãĤ½
    0.77
    PsyNetMessage
    0.70
    ahime
    0.69
    ãĥĺ
    0.68
    lessness
    0.67
    isms
    0.67
    >[
    0.67
    itiveness
    0.66
    inition
    0.66
    lations
    0.65
    Activations Density 0.475%

    No Known Activations