INDEX

Explanations

phrases relating to transactions or exchanges involving tangible items 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.88

GEBURTS

-0.81

RenderAtEndOf

-0.77

.*")]

-0.72

Hentet

-0.71

таратура

-0.68

IntoConstraints

-0.67

makeConstraints

-0.65

:✨

-0.65

 doInBackground

-0.65

POSITIVE LOGITS

 resell

0.94

 reuse

0.78

 resold

0.76

 then

0.75

 distribute

0.72

 resale

0.69

 sell

0.68

 later

0.67

use

0.66

 revend

0.66

Activations Density 0.585%

phrases relating to transactions or exchanges involving tangible items or concepts

No Comments

No Known Activations