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. 3363
    Prev
    Next
    INDEX
    Explanations

    expressions related to construction and building

    oai_token-act-pair · gpt-3.5-turbo

    specific company names and related entities

    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
    querque
    -0.65
    ufact
    -0.63
    vertisement
    -0.61
    ubi
    -0.58
    arcity
    -0.54
    icipated
    -0.54
    assador
    -0.54
     Lauder
    -0.52
    isible
    -0.51
    anwhile
    -0.51
    POSITIVE LOGITS
     Poles
    0.57
    hei
    0.55
    wagen
    0.53
     edges
    0.52
    nels
    0.49
    lde
    0.48
    âĦ¢:
    0.48
    ´
    0.48
    Scale
    0.48
     polyg
    0.47
    Activations Density 1.287%

    No Known Activations