INDEX

Explanations

occurrences of the word "find" and its variants, suggesting a focus on discovery or realization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MathML

-0.71

BorderFactory

-0.67

httphttps

-0.66

labus

-0.65

 внимание

-0.64

Pais

-0.63

zzleHttp

-0.62

 lenker

-0.60

 torr

-0.60

/****

-0.60

POSITIVE LOGITS

 FIND

1.23

FIND

1.18

 Finds

1.14

find

1.06

 finds

1.01

 find

0.98

 Findlay

0.96

Find

0.94

 Find

0.91

finds

0.90

Activations Density 0.158%

occurrences of the word "find" and its variants, suggesting a focus on discovery or realization

No Comments

No Known Activations