© 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. 3-RES-JB
    11. 11334
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.80
    semble
    -0.78
    fell
    -0.74
    è¦ļéĨĴ
    -0.66
    SPONSORED
    -0.62
    ammy
    -0.62
    eding
    -0.61
    mitter
    -0.61
    techn
    -0.61
    workers
    -0.59
    POSITIVE LOGITS
    reprene
    0.89
    urities
    0.73
     warr
    0.69
     revenge
    0.66
    htar
    0.66
    istani
    0.65
     pus
    0.64
     extrad
    0.63
     to
    0.63
     applause
    0.62
    Activations Density 0.077%

    No Known Activations