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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 15144
    Prev
    Next
    INDEX
    Explanations

    references to different tiers, such as Tier 7, Tier 8, and Tier 9

    oai_token-act-pair · gpt-3.5-turbo

    references to hierarchical classifications or levels, particularly regarding tiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okia
    -0.86
    issance
    -0.81
    mercial
    -0.71
    hur
    -0.70
     Liberties
    -0.61
    sky
    -0.61
    ãĥĻ
    -0.60
     Evening
    -0.59
    natureconservancy
    -0.58
     Predators
    -0.58
    POSITIVE LOGITS
     tiers
    0.86
     tier
    0.82
    uple
    0.80
     guiActiveUnfocused
    0.74
    arity
    0.74
    ney
    0.73
    neys
    0.72
    Tier
    0.68
     bracket
    0.67
    anza
    0.65
    Activations Density 0.026%

    No Known Activations