INDEX

Explanations

references to specific programs or educational initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

WriteTagHelper

-1.01

 disambiguazione

-0.96

LookAnd

-0.94

بوابة

-0.92

 snippetHide

-0.92

TagMode

-0.92

 onOptions

-0.88

#+#

-0.88

Datuak

-0.87

RenderAtEndOf

-0.87

POSITIVE LOGITS

과

0.51

 readily

0.50

<sup>

0.49

 significant

0.49

 finir

0.48

 with

0.47

 developments

0.46

npos

0.45

ворю

0.45

Activations Density 0.145%

references to specific programs or educational initiatives

No Comments

No Known Activations