INDEX

Explanations

occurrences of the letter 't' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 suced

-0.54

PEAT

-0.48

FORMAN

-0.47

and

-0.46

zwungen

-0.46

fır

-0.46

gatan

-0.46

Hansen

-0.46

 ramai

-0.45

 kema

-0.45

POSITIVE LOGITS

 Monfieur

1.15

 deſt

1.14

 pleaſure

1.11

 purpoſe

1.10

 cauſe

1.08

 ſtate

1.06

 leaſt

1.05

 itſelf

1.05

Билгалдахарш

1.04

 preſent

1.03

Activations Density 0.141%

occurrences of the letter 't' in various contexts

No Comments

No Known Activations