© 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. 0-RES-JB
    11. 8110
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love or strong affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alphabet
    -0.71
     indebted
    -0.70
     arms
    -0.65
     Crimson
    -0.65
     hob
    -0.65
     overs
    -0.65
     proceedings
    -0.64
     herald
    -0.63
     intermedi
    -0.63
     eventual
    -0.62
    POSITIVE LOGITS
    VE
    4.24
    ve
    2.02
    VP
    1.56
    VER
    1.52
    VEL
    1.50
    ZE
    1.50
    VO
    1.50
    Ve
    1.48
    ves
    1.43
    VEN
    1.41
    Activations Density 0.010%

    No Known Activations