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. 5-RES-JB
    6. 17068
    Prev
    Next
    INDEX
    Explanations

    places or concepts that provide safety or support

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to safety, protection, and support systems

    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
    ancies
    -0.80
    qus
    -0.78
    intent
    -0.70
    ntax
    -0.67
     staggered
    -0.65
    yss
    -0.64
    itars
    -0.64
    ©¶æ
    -0.64
    wagen
    -0.64
    erity
    -0.62
    POSITIVE LOGITS
     reminder
    0.87
     beacon
    0.81
     fodder
    0.76
     discipl
    0.76
    piece
    0.76
     anthem
    0.75
     entry
    0.74
     gateway
    0.72
    inel
    0.71
     magnet
    0.70
    Activations Density 0.303%

    No Known Activations