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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RES-JB
    6. 21185
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or requiring permission or consent

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and terms related to consent and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orie
    -0.85
    ahime
    -0.79
    okes
    -0.74
    é¾
    -0.74
    odcast
    -0.72
    iple
    -0.70
    amed
    -0.69
    foundland
    -0.68
    pire
    -0.68
    rose
    -0.65
    POSITIVE LOGITS
     consent
    1.55
     assistance
    1.54
     blessing
    1.53
     permission
    1.50
     approval
    1.43
     help
    1.43
     cooperation
    1.42
     support
    1.31
     aid
    1.31
     backing
    1.26
    Activations Density 0.195%

    No Known Activations