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. 1-RES-JB
    6. 17493
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions related to rear parts of objects or devices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "rear" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensable
    -0.81
    ogl
    -0.79
    AMI
    -0.75
    helps
    -0.75
    âĸĪâĸĪ
    -0.71
    ACA
    -0.69
    argon
    -0.67
    gans
    -0.67
    olver
    -0.66
    ongo
    -0.66
    POSITIVE LOGITS
    ward
    0.97
     axle
    0.93
     rear
    0.92
     tyre
    0.87
     derail
    0.81
    side
    0.80
    stairs
    0.79
    door
    0.79
    wash
    0.74
     torque
    0.73
    Activations Density 0.009%

    No Known Activations