INDEX

Explanations

instances of the word "this" indicating references to current topics or information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 HasFactory

-0.72

etheless

-0.69

 betweenstory

-0.65

RTDA

-0.63

 riman

-0.62

 slightest

-0.57

ificance

-0.57

)');

-0.56

RUnlock

-0.56

vato

-0.56

POSITIVE LOGITS

 spake

0.51

 poveznice

0.49

templateUrl

0.48

ModelBuilder

0.47

Is

0.46

Content

0.46

 createState

0.46

ječ

0.45

Comté

0.44

SizeF

0.44

Activations Density 0.156%

instances of the word "this" indicating references to current topics or information

No Comments

No Known Activations