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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5508
    Prev
    Next
    INDEX
    Explanations

    instances where the word "hope" is mentioned with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hope or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDER
    -0.87
    IGN
    -0.75
    idelines
    -0.68
    ocaust
    -0.68
    ipolar
    -0.67
    mouth
    -0.67
    hips
    -0.66
    ANT
    -0.65
    als
    -0.65
    ONT
    -0.64
    POSITIVE LOGITS
     someday
    0.94
     outcome
    0.74
     opio
    0.69
    eday
    0.66
     whoever
    0.66
     justifies
    0.65
     interval
    0.63
     they
    0.63
     someone
    0.62
     Russians
    0.61
    Activations Density 0.164%

    No Known Activations