© 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. 12864
    Prev
    Next
    INDEX
    Explanations

    words related to completing tasks or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions or requirements for achieving success

    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
    ccording
    -0.80
     helicop
    -0.79
    ©¶æ
    -0.79
     millenn
    -0.73
    ¥ŀ
    -0.73
     livest
    -0.71
     tremend
    -0.67
    ortunately
    -0.65
    etheless
    -0.64
    ModLoader
    -0.64
    POSITIVE LOGITS
    )=(
    0.72
    ificate
    0.63
    ivation
    0.63
    Item
    0.61
    edIn
    0.61
    CAST
    0.61
    rina
    0.60
    ain
    0.58
    ÑĢ
    0.57
     Ø
    0.55
    Activations Density 0.118%

    No Known Activations