INDEX

Explanations

phrases involving possessive pronouns or contractions related to ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

non

-0.83

 long

-0.75

set

-0.75

so

-0.74

 real

-0.73

far

-0.73

ronom

-0.72

 fine

-0.71

mặt

-0.71

POSITIVE LOGITS

 ſever

0.92

 itſelf

0.90

 houſe

0.89

 مرئيه

0.87

 greateſt

0.87

 myſelf

0.86

 Majefty

0.86

 ſche

0.86

 pleaſure

0.85

 Houſe

0.84

Activations Density 0.033%

phrases involving possessive pronouns or contractions related to ownership or association

No Comments

No Known Activations