INDEX

Explanations

occurrences of the word "do" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 houſe

-1.01

 ſche

-0.98

 itſelf

-0.86

 stiefel

-0.86

 ſever

-0.86

Efq

-0.85

 Jefus

-0.85

 <<<<<<<<<<<<<<

-0.85

 themſelves

-0.84

 pleaſure

-0.84

POSITIVE LOGITS

do

1.47

 done

1.25

 does

1.24

Do

1.22

 doing

1.19

Do

1.17

 Doing

1.15

did

1.13

Doing

1.11

 DOING

1.10

Activations Density 0.157%

occurrences of the word "do" and its variations

No Comments

No Known Activations