© 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. 19410
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving, receiving, or causing actions to be done to others

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating direction or guidance actions

    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
     Confeder
    -0.66
     ours
    -0.60
     formation
    -0.60
    tein
    -0.59
    insula
    -0.57
     convergence
    -0.57
     tradition
    -0.56
    Austral
    -0.55
     genesis
    -0.55
     UDP
    -0.55
    POSITIVE LOGITS
     aback
    0.99
    by
    0.78
     by
    0.76
    ardless
    0.70
    quished
    0.69
    wic
    0.69
    ©¶æ¥µ
    0.69
    ifferent
    0.68
    graded
    0.68
    pez
    0.67
    Activations Density 0.249%

    No Known Activations