INDEX

Explanations

frequent occurrences of the verb "to be" in various forms

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

 purpoſe

-1.04

 ſtate

-1.01

 pleaſure

-1.01

 ſever

-0.98

 myſelf

-0.98

 Chriftian

-0.97

 raiſ

-0.97

 uſed

-0.96

 houſe

-0.95

 ſeveral

-0.93

POSITIVE LOGITS

is

1.81

was

1.34

are

1.31

not

1.30

 also

1.17

1.12

be

1.12

 being

1.12

Is

1.09

 indeed

1.08

Activations Density 1.468%

frequent occurrences of the verb "to be" in various forms

No Comments

No Known Activations