INDEX

Explanations

strings or sequences related to coding or programming constructs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.88

expandindo

-0.88

 himſelf

-0.87

sizeCache

-0.86

 chofe

-0.86

 Spisak

-0.85

ſelf

-0.84

HasForeignKey

-0.84

 ISNI

-0.83

 raiſ

-0.82

POSITIVE LOGITS

[toxicity=0]

0.52

</strong>

0.48

0.47

ństwa

0.45

...

0.45

orghe

0.44

falen

0.43

 otherwise

0.42

</b>

0.42

Activations Density 0.433%

strings or sequences related to coding or programming constructs

No Comments

No Known Activations