INDEX

Explanations

occurrences of the term "ve" and its variations, likely relating to a specific subject or concept

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

 Majefty

-1.03

 themſelves

-0.97

 Diſ

-0.96

 himſelf

-0.96

 itſelf

-0.94

 myſelf

-0.93

 pleaſure

-0.92

 Jefus

-0.91

 purpoſe

-0.88

Efq

-0.87

POSITIVE LOGITS

Ve

1.07

Ve

0.93

ve

0.81

VE

0.81

VE

0.79

 та

0.69

Et

0.67

et

0.64

ET

0.61

ve

0.59

Activations Density 0.170%

occurrences of the term "ve" and its variations, likely relating to a specific subject or concept

No Comments

No Known Activations