INDEX

Explanations

occurrences of the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Humphreys

-0.66

ANDRA

-0.65

newtheorem

-0.64

 dicha

-0.64

zke

-0.63

CppMethod

-0.63

FOOTNOTES

-0.63

SOT

-0.62

larak

-0.62

CodeAttribute

-0.61

POSITIVE LOGITS

 Agrega

0.76

 Linz

0.72

 dedans

0.71

LookAnd

0.67

 giù

0.66

Positives

0.64

 roulant

0.64

Admissions

0.64

 Upan

0.63

 curé

0.62

Activations Density 0.132%

occurrences of the word "in"

No Comments

No Known Activations