© 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. 7-RES-JB
    11. 23375
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempting or striving

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trying."

    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
    dylib
    -0.76
    oola
    -0.68
    anon
    -0.64
    lav
    -0.61
    cised
    -0.60
    ros
    -0.60
    thus
    -0.59
    ifa
    -0.59
    spread
    -0.58
    friends
    -0.58
    POSITIVE LOGITS
     unsuccessfully
    1.07
     desperately
    0.98
     harder
    0.90
    ioned
    0.73
    reprene
    0.72
     vain
    0.71
     valiant
    0.71
     frantically
    0.70
    ggle
    0.66
    ison
    0.66
    Activations Density 0.050%

    No Known Activations