© 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. 21186
    Prev
    Next
    INDEX
    Explanations

    phrases related to revisiting or bringing back old things

    oai_token-act-pair · gpt-3.5-turbo

    action words related to renewal or transformation

    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
    osponsors
    -0.72
    starter
    -0.67
    twitter
    -0.66
     glim
    -0.66
     teasp
    -0.66
    -----------
    -0.65
    fin
    -0.64
     confir
    -0.64
    Streamer
    -0.64
     distingu
    -0.63
    POSITIVE LOGITS
     notions
    0.90
     classics
    0.90
     myths
    0.88
     memories
    0.87
     old
    0.85
     stereotypes
    0.84
     existing
    0.83
     classic
    0.81
     obsolete
    0.79
     outdated
    0.78
    Activations Density 0.355%

    No Known Activations