© 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. 9-RES-JB
    11. 21179
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intent to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.63
    ibliography
    -0.61
    auer
    -0.60
    gdala
    -0.60
    ielding
    -0.59
    ranean
    -0.59
    trust
    -0.58
    soever
    -0.58
    è¦ļéĨĴ
    -0.58
    voc
    -0.57
    POSITIVE LOGITS
     something
    0.91
     clarification
    0.91
     to
    0.83
     revenge
    0.79
     someone
    0.76
     clarity
    0.74
     answers
    0.73
     permission
    0.73
     assurances
    0.73
     somebody
    0.72
    Activations Density 0.103%

    No Known Activations