© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23613
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "trying to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey attempts or intentions

    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
    most
    -0.68
     Clouds
    -0.63
     Rising
    -0.62
     Returning
    -0.61
     Appears
    -0.60
     Cros
    -0.59
     Houses
    -0.59
    ILY
    -0.57
     Vol
    -0.56
     Lag
    -0.56
    POSITIVE LOGITS
     recreate
    1.23
     emulate
    1.21
     convince
    1.16
     imitate
    1.15
     revive
    1.14
     replicate
    1.12
     conserve
    1.11
     reconcile
    1.10
     establish
    1.06
     eliminate
    1.06
    Activations Density 0.075%

    No Known Activations