© 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. 9-RES-JB
    11. 18627
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disappointment or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disappointment or lamentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pyramid
    -0.61
     guiActiveUn
    -0.61
     subordinate
    -0.61
     disguise
    -0.57
     horr
    -0.57
     anat
    -0.56
     Picture
    -0.55
    opian
    -0.54
     complicit
    -0.54
     part
    -0.54
    POSITIVE LOGITS
    been
    1.33
     been
    1.08
    gotten
    0.97
     gotten
    0.90
     Been
    0.90
    shown
    0.83
    ered
    0.80
    lled
    0.79
     fallen
    0.78
    ished
    0.76
    Activations Density 0.057%

    No Known Activations