INDEX

Explanations

references to financial or economic terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-0.55

-0.51

 specific

-0.50

re

-0.49

qu

-0.49

-0.48

 near

-0.47

ma

-0.47

POSITIVE LOGITS

 חיצוניים

0.82

 myſelf

0.77

 itſelf

0.75

ſelves

0.70

 HasFactory

0.69

 autorytatywna

0.68

 Jefus

0.65

ſelf

0.64

 ſind

0.63

VIAF

0.63

Activations Density 0.069%

references to financial or economic terms

No Comments

No Known Activations