© 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. 11-RES-JB
    11. 22673
    Prev
    Next
    INDEX
    Explanations

    comparatives and superlatives indicating degrees of significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant or substantial changes or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dreams
    -0.83
    emet
    -0.75
     Releases
    -0.71
    urities
    -0.68
     MISS
    -0.68
     FANTASY
    -0.67
     Guys
    -0.67
    aturday
    -0.67
     Missing
    -0.67
     Characters
    -0.66
    POSITIVE LOGITS
     stringent
    1.48
     restrictive
    1.43
     punitive
    1.31
     expansive
    1.25
     draconian
    1.25
     len
    1.24
     aggressive
    1.20
     ambitious
    1.19
     rigorous
    1.18
     intrusive
    1.16
    Activations Density 0.239%

    No Known Activations