© 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. 4379
    Prev
    Next
    INDEX
    Explanations

    terms related to specific topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with topics of relevance or connection to specific subjects

    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
    ypes
    -0.75
    agne
    -0.74
    CHA
    -0.69
    IPP
    -0.65
     Frankenstein
    -0.65
     Brist
    -0.62
    ÄŁ
    -0.62
    Assad
    -0.60
     Petra
    -0.60
    abi
    -0.59
    POSITIVE LOGITS
     pertaining
    0.95
    adequ
    0.79
    eering
    0.74
    tains
    0.72
    merce
    0.71
    ences
    0.70
     relating
    0.70
     thereto
    0.70
    gest
    0.68
     conduc
    0.67
    Activations Density 0.009%

    No Known Activations