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. 170
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location - Breton port city

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Bre" followed by various terms related to a location or context

    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
    iating
    -0.77
     Fired
    -0.74
     guiActiveUnfocused
    -0.71
    å°Ĩ
    -0.71
    iated
    -0.69
     unsustainable
    -0.67
    ONES
    -0.67
     roadside
    -0.66
     terr
    -0.65
    iants
    -0.64
    POSITIVE LOGITS
    thren
    1.19
    akers
    1.10
    aks
    1.07
    vity
    1.03
    acher
    1.03
    eding
    1.02
    aker
    1.02
    cker
    1.00
    aches
    0.98
    chet
    0.98
    Activations Density 0.018%

    No Known Activations