INDEX

Explanations

phrases that indicate non-obligatory actions or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

twimg

-0.82

Xna

-0.54

wts

-0.54

saraba

-0.53

WithIOException

-0.53

⎨

-0.52

codings

-0.52

Aplica

-0.52

ագրություններ

-0.51

elemField

-0.51

POSITIVE LOGITS

 GoogleFonts

0.74

 kasarigan

0.66

 mand

0.52

 alternatively

0.49

 Глав

0.47

 nutricional

0.47

なくても

0.46

ньому

0.45

ⓧ

0.45

 loosely

0.45

Activations Density 0.266%

phrases that indicate non-obligatory actions or choices

No Comments

No Known Activations