© 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. 2-RES-JB
    11. 17722
    Prev
    Next
    INDEX
    Explanations

    verbs related to expressing grief or sorrow and adjectives related to expressing strong disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    words expressing sorrow or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.84
    chedel
    -0.79
    NetMessage
    -0.78
    ramid
    -0.75
    chn
    -0.75
    ahon
    -0.73
    cius
    -0.73
    tein
    -0.72
    smoking
    -0.71
    emade
    -0.68
    POSITIVE LOGITS
     lament
    0.90
     lamented
    0.87
     depl
    0.80
    aste
    0.78
    ãģį
    0.77
    verse
    0.75
    ably
    0.75
     Canaver
    0.74
    880
    0.74
    anty
    0.72
    Activations Density 0.016%

    No Known Activations