INDEX

Explanations

references to discoveries, especially in legal or investigative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 <=",

-0.64

 crainte

-0.55

 Known

-0.50

 seen

-0.50

thâu

-0.50

 seeing

-0.49

known

-0.48

 veder

-0.48

Concerns

-0.48

jmniej

-0.48

POSITIVE LOGITS

 lurking

0.84

 among

0.81

 amongst

0.76

 parmi

0.73

 среди

0.72

 buried

0.71

 hiding

0.69

among

0.68

 wśród

0.68

 wandering

0.67

Activations Density 0.223%

references to discoveries, especially in legal or investigative contexts

No Comments

No Known Activations