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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 15860
    Prev
    Next
    INDEX
    Explanations

    phrases related to aspirations and values

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social issues and community dynamics

    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
    ppa
    -0.55
     limb
    -0.55
     snaps
    -0.54
     Volunte
    -0.54
    eb
    -0.53
    database
    -0.53
    iken
    -0.52
    pm
    -0.52
    iff
    -0.51
     Pastebin
    -0.51
    POSITIVE LOGITS
    ynchronous
    0.67
    cum
    0.62
    within
    0.60
    WithNo
    0.60
     embodied
    0.58
    arently
    0.58
     whose
    0.58
    otten
    0.57
     nonetheless
    0.57
    comed
    0.57
    Activations Density 0.419%

    No Known Activations