© 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. 6-RES-JB
    11. 7719
    Prev
    Next
    INDEX
    Explanations

    phrases with the prefix "well-" followed by a descriptive word

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating being well-known or well-publicized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phi
    -0.78
     Compass
    -0.74
    ulhu
    -0.70
     Slide
    -0.69
     Pok
    -0.68
     Noir
    -0.68
     TAMADRA
    -0.68
     Midnight
    -0.68
     Bravo
    -0.67
     beads
    -0.67
    POSITIVE LOGITS
    enough
    1.21
    sized
    1.12
    connected
    1.11
    defined
    1.09
    known
    1.07
    trained
    1.07
    informed
    1.06
    founded
    1.06
    established
    1.06
    educated
    1.06
    Activations Density 0.035%

    No Known Activations