© 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. 9224
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative actions or events

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases that imply criticism or conflict

    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
    ously
    -0.75
    HL
    -0.64
    edo
    -0.61
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.60
    /(
    -0.58
    oks
    -0.58
    xes
    -0.57
    entials
    -0.57
    :[
    -0.56
    .):
    -0.56
    POSITIVE LOGITS
    _-
    1.74
    webkit
    0.89
    =-=-=-=-=-=-=-=-
    0.83
     ie
    0.77
     [|
    0.76
    /-
    0.74
    =-=-=-=-
    0.74
    named
    0.71
    cens
    0.69
    enough
    0.69
    Activations Density 0.066%

    No Known Activations