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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16858
    Prev
    Next
    INDEX
    Explanations

    movie or book reviews with a verdict

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dict" which is likely related to the concept of prediction or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cam
    -0.67
     interviews
    -0.66
     mic
    -0.65
     ultraviolet
    -0.64
     disability
    -0.62
     live
    -0.61
     clubs
    -0.60
     wheelchair
    -0.60
     broadcasting
    -0.59
     plac
    -0.59
    POSITIVE LOGITS
    dict
    4.53
    math
    1.26
    gence
    0.97
    dit
    0.96
    imov
    0.95
    claimer
    0.91
    ilogy
    0.90
    ict
    0.90
    rules
    0.87
    redients
    0.87
    Activations Density 0.007%

    No Known Activations