© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to honest and open communication

    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
    ģĸ
    -0.72
    aredevil
    -0.65
    aunders
    -0.63
    yre
    -0.61
    hire
    -0.60
    ynski
    -0.59
    hesda
    -0.59
    gerald
    -0.58
    vous
    -0.58
     disadvant
    -0.57
    POSITIVE LOGITS
     aloud
    1.19
     louder
    1.10
     loudly
    0.98
     behalf
    0.84
     loud
    0.83
     language
    0.82
     talk
    0.81
     tongues
    0.79
    podcast
    0.79
    language
    0.77
    Activations Density 0.227%

    No Known Activations