INDEX

Explanations

instances of the word "to," particularly in contexts indicating purpose or direction

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-0.71

jetbrains

-0.68

 Chriſt

-0.66

 eenige

-0.65

Personensuche

-0.65

ImageContext

-0.65

 étoit

-0.65

 venait

-0.64

 ſon

-0.62

 exig

-0.62

POSITIVE LOGITS

 make

0.90

be

0.89

 take

0.86

put

0.84

 have

0.82

 bring

0.77

do

0.76

 give

0.75

 look

0.73

 stop

0.73

Activations Density 0.744%

instances of the word "to," particularly in contexts indicating purpose or direction

No Comments

No Known Activations