© 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. 4462
    Prev
    Next
    INDEX
    Explanations

    numbers related to international summits or conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to international meetings and conferences

    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
     deserted
    -0.70
     rushed
    -0.68
     scattered
    -0.68
     teasp
    -0.65
     earthqu
    -0.64
     sho
    -0.64
    retch
    -0.64
     srfAttach
    -0.63
     gren
    -0.62
    undred
    -0.62
    POSITIVE LOGITS
    DM
    0.88
    xual
    0.87
    Ds
    0.83
    Cs
    0.80
    HS
    0.80
    GS
    0.76
    âĢ²
    0.75
    eus
    0.74
    DS
    0.74
    Es
    0.72
    Activations Density 0.188%

    No Known Activations