INDEX

Explanations

references to data or statistical analysis conventions, particularly in a scientific or technical context

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

 disponibilités

-0.74

KommentareTeilen

-0.72

脚注の使い方

-0.71

 يتيمه

-0.68

ⓧ

-0.65

出版年

-0.63

findpost

-0.62

stdc

-0.60

 autorytatywna

-0.60

#+#

-0.59

POSITIVE LOGITS

Fig

0.77

see

0.76

Figure

0.72

 Figure

0.68

see

0.67

Table

0.67

Fig

0.66

hence

0.66

buttonBar

0.62

例えば

0.62

Activations Density 0.685%

references to data or statistical analysis conventions, particularly in a scientific or technical context

No Comments

No Known Activations