© 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. 1403
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical data related to performance averages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical averages or performance metrics

    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
    abet
    -0.72
     Nou
    -0.70
    ACTED
    -0.70
     Starship
    -0.67
    ighter
    -0.66
     Rey
    -0.66
    bis
    -0.64
    Drug
    -0.64
    raft
    -0.64
    gravity
    -0.63
    POSITIVE LOGITS
     averages
    1.11
     averaging
    0.98
     averaged
    0.95
    icals
    0.87
    imates
    0.87
     avg
    0.84
    mble
    0.80
     ILCS
    0.79
     unbeliev
    0.77
    ically
    0.77
    Activations Density 0.008%

    No Known Activations