INDEX

Explanations

instances of the letter "s" 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

and

-0.54

-0.53

-0.49

 they

-0.46

in

-0.46

 with

-0.46

has

-0.46

↵↵

-0.45

They

-0.44

POSITIVE LOGITS

NUMX

1.18

ſelves

1.17

 fevere

1.17

 greateſt

1.13

 Chriſt

1.13

 Jefus

1.10

UIControlState

1.10

 Theſe

1.09

](#

1.09

ſelf

1.07

Activations Density 0.091%

instances of the letter "s" in various contexts

No Comments

No Known Activations