INDEX

Explanations

phrases emphasizing conditions or consequences that include the word "that."

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

 disponibilités

-0.70

uous

-0.68

 ratify

-0.68

 Hecht

-0.64

 snowing

-0.62

 inauguration

-0.60

̈́

-0.60

Aktuelle

-0.60

dė

-0.60

 seyn

-0.59

POSITIVE LOGITS

who

1.13

 which

1.06

which

0.93

 that

0.91

who

0.89

 والذي

0.85

[]:

0.84

 joka

0.83

yg

0.82

qui

0.81

Activations Density 0.445%

phrases emphasizing conditions or consequences that include the word "that."

No Comments

No Known Activations