Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1172
    Prev
    Next
    INDEX
    Explanations

    keywords related to the rear of objects or devices

    oai_token-act-pair · gpt-3.5-turbo

    references to the rear part of objects or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸĪâĸĪ
    -0.85
    ensable
    -0.80
    argon
    -0.77
    helps
    -0.75
    ittee
    -0.75
    esson
    -0.74
    âĸĪâĸĪâĸĪâĸĪ
    -0.73
    achu
    -0.72
    aepernick
    -0.70
    ACA
    -0.69
    POSITIVE LOGITS
    ward
    1.11
     axle
    0.97
     tyre
    0.89
    wash
    0.82
     rotor
    0.81
     lobe
    0.80
    bone
    0.78
    side
    0.78
     rear
    0.75
     derail
    0.75
    Activations Density 0.008%

    No Known Activations