© 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. 3876
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotions or attitudes of sincerity or dedication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to kindness or warmth versus coldness and cruel behavior

    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
    Downloadha
    -0.83
    ggies
    -0.71
    assic
    -0.66
    ICH
    -0.64
    andra
    -0.64
    ICO
    -0.64
    abases
    -0.63
    MAT
    -0.61
    JO
    -0.60
    Indust
    -0.60
    POSITIVE LOGITS
    hearted
    1.32
    ness
    0.86
    heartedly
    0.82
    tons
    0.74
     endeavour
    0.72
    terness
    0.70
    nesses
    0.69
     glances
    0.68
    acters
    0.68
     altru
    0.68
    Activations Density 0.006%

    No Known Activations