INDEX

Explanations

mentions of specific names and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 myſelf

-0.96

 pleaſure

-0.94

 ExecuteAsync

-0.91

 itſelf

-0.87

 Houſe

-0.86

Efq

-0.85

LookAnd

-0.85

ſelf

-0.84

 whoſe

-0.84

 houſe

-0.82

POSITIVE LOGITS

0.48

보

0.40

 Donald

0.40

梨

0.40

 perla

0.40

TURE

0.39

 caras

0.39

ابقة

0.38

 kasarigan

0.37

Activations Density 0.321%

mentions of specific names and characters

No Comments

No Known Activations