INDEX

Explanations

references to legal terminology or concepts

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

AndEndTag

-0.97

 betweenstory

-0.88

thâu

-0.75

 referenties

-0.75

("]");

-0.74

SharedCtor

-0.74

parsedMessage

-0.73

TagHelper

-0.72

 незавершена

-0.70

 ExecuteAsync

-0.69

POSITIVE LOGITS

Conversely

1.88

 conversely

1.86

 Conversely

1.86

 meanwhile

1.70

 contrast

1.55

 dagegen

1.46

 contrary

1.45

on

1.41

 hingegen

1.40

另一方面

1.35

Activations Density 0.289%

references to legal terminology or concepts

No Comments

No Known Activations