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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11196
    Prev
    Next
    INDEX
    Explanations

    details or components related to the physical structure of an object or entity, especially focusing on the front or rear parts

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicle parts, particularly focusing on the front and rear sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emonic
    -0.82
    istani
    -0.81
    imore
    -0.80
    20439
    -0.76
    akable
    -0.72
    atoon
    -0.72
    arak
    -0.71
    NI
    -0.69
    ongo
    -0.69
     Slay
    -0.69
    POSITIVE LOGITS
     diameter
    1.10
     casing
    0.97
    most
    0.94
     lobe
    0.93
     circumference
    0.92
     shaft
    0.90
     rim
    0.89
     cavity
    0.88
     torso
    0.85
     pane
    0.84
    Activations Density 0.098%

    No Known Activations