© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4045
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "Don't" followed by a varying degree of emphasis on what follows

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "don't" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Codec
    -0.71
     Frag
    -0.70
     Gmail
    -0.69
     notebooks
    -0.68
     Scrib
    -0.67
     fragmentation
    -0.66
     AAC
    -0.66
     Hollywood
    -0.64
     bombshell
    -0.64
     Kaf
    -0.63
    POSITIVE LOGITS
    tre
    1.07
    own
    1.05
    ¹
    1.04
    t
    1.03
    eal
    1.01
    vest
    1.00
    sent
    1.00
    ought
    0.99
    eri
    0.98
    td
    0.97
    Activations Density 0.205%

    No Known Activations