INDEX

Explanations

references to the concept of "it" in various contexts, indicating a focus on identifying pronouns and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 garda

-0.73

 policiales

-0.68

 επίσης

-0.68

 asimismo

-0.66

 egli

-0.64

ValueStyle

-0.62

Хочу

-0.61

 préféré

-0.60

adpleegd

-0.59

THISDAY

-0.59

POSITIVE LOGITS

 BoxFit

0.70

It

0.69

It

0.69

it

0.64

AddTagHelper

0.60

The

0.57

">{{$

0.57

 happened

0.56

шло

0.56

ça

0.51

Activations Density 0.224%

references to the concept of "it" in various contexts, indicating a focus on identifying pronouns and their usage

No Comments

No Known Activations