INDEX

Explanations

instances of the word "of"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 pleaſure

-1.09

 houſe

-0.93

 itſelf

-0.88

 raiſ

-0.85

Efq

-0.84

 purpoſe

-0.84

 fhort

-0.77

 fufficient

-0.76

 himſelf

-0.75

 cauſe

-0.75

POSITIVE LOGITS

of

0.94

ReusableCell

0.94

the

0.90

aarrggbb

0.87

+#+#

0.84

 these

0.82

onAttach

0.79

 their

0.78

providedIn

0.78

setof

0.78

Activations Density 0.081%

instances of the word "of"

No Comments

No Known Activations