© 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. 13135
    Prev
    Next
    INDEX
    Explanations

    words related to expressions of opinion, particularly strong emotions like love and hate, as well as making decisions and taking actions

    oai_token-act-pair · gpt-3.5-turbo

    capitalized letters and specific pronouns in usage contexts

    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
     poly
    -0.67
     portraits
    -0.64
    poly
    -0.63
     poppy
    -0.62
    coni
    -0.62
     fragmentation
    -0.61
     glob
    -0.60
    tics
    -0.60
     kits
    -0.59
     sandbox
    -0.58
    POSITIVE LOGITS
    ounced
    1.12
    ained
    1.09
    ought
    1.08
    overed
    1.07
    OULD
    1.03
    owed
    1.01
    stood
    0.97
    ighed
    0.94
    aped
    0.94
    ACTED
    0.91
    Activations Density 0.197%

    No Known Activations