© 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. 7258
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events happening without certain requirements or permissions

    oai_token-act-pair · gpt-3.5-turbo
    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
     âĢº
    -0.86
    estate
    -0.86
    soDeliveryDate
    -0.84
    ahime
    -0.77
    MAP
    -0.76
     Rooms
    -0.74
    çĶ°
    -0.74
    terness
    -0.73
    代
    -0.70
    geist
    -0.70
    POSITIVE LOGITS
     knowledge
    1.01
     interruption
    0.96
     intervention
    0.86
     permission
    0.85
     knowing
    0.82
     recourse
    0.82
     doubt
    0.80
     supervision
    0.78
     fuss
    0.77
     detectable
    0.76
    Activations Density 0.082%

    No Known Activations