© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2735
    Prev
    Next
    INDEX
    Explanations

    keywords related to new product releases and innovations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of new products or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.80
    emies
    -0.70
    assian
    -0.69
    WOOD
    -0.68
    oldemort
    -0.68
    chan
    -0.68
    woods
    -0.67
    soType
    -0.67
    oil
    -0.67
    wood
    -0.66
    POSITIVE LOGITS
     ease
    1.04
     regards
    0.98
     unprecedented
    0.95
     announcements
    0.92
     victories
    0.89
     innovative
    0.88
     sheer
    0.88
     groundbreaking
    0.86
     impunity
    0.85
     astounding
    0.85
    Activations Density 0.179%

    No Known Activations