INDEX

Explanations

past tense verbs and words that indicate actions taken

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 purpoſe

-0.88

 reaſon

-0.83

 raiſ

-0.82

 héro

-0.79

 myſelf

-0.78

 deſt

-0.78

 ſhe

-0.77

 becauſe

-0.76

 pleaſure

-0.75

 himſelf

-0.75

POSITIVE LOGITS

ContentAsync

0.54

numerusform

0.53

 Eing

0.51

 would

0.51

 hoped

0.48

vor

0.47

SpringRunner

0.47

ab

0.45

rawDesc

0.44

]:

0.44

Activations Density 0.923%

past tense verbs and words that indicate actions taken

No Comments

No Known Activations

past tense verbs and words that indicate actions taken

No Comments

No Known Activations