© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 22893
    Prev
    Next
    INDEX
    Explanations

    instances of actions or situations that require consent

    oai_token-act-pair · gpt-3.5-turbo

    references to consent and authorization in scenarios involving actions taken without permission

    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
     Tycoon
    -0.71
     Ange
    -0.66
    nai
    -0.61
    oir
    -0.61
     Christy
    -0.60
     MAP
    -0.60
    esta
    -0.59
    icent
    -0.58
     rall
    -0.58
     Ashton
    -0.58
    POSITIVE LOGITS
     whatsoever
    1.21
    dding
    0.84
     nor
    0.72
     provocation
    0.69
    oldown
    0.66
     interruption
    0.66
    angering
    0.65
     anymore
    0.64
    animous
    0.64
    pection
    0.63
    Activations Density 0.128%

    No Known Activations