INDEX

Explanations

phrases indicating authorship or leadership in a context

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

IsContent

-0.77

 pleaſure

-0.74

tagHelper

-0.66

 purpoſe

-0.62

 ſche

-0.59

 faſt

-0.59

mità

-0.58

riwal

-0.57

 diſt

-0.56

 houſe

-0.55

POSITIVE LOGITS

حوالہ

0.72

 geslacht

0.68

 Emeritus

0.65

 oleh

0.62

 emeritus

0.62

 kasarigan

0.61

 qualified

0.61

 former

0.60

Lähteet

0.59

by

0.56

Activations Density 0.375%

phrases indicating authorship or leadership in a context

No Comments

No Known Activations