INDEX

Explanations

instances of words related to comparisons and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 continuant

-0.68

necedor

-0.68

enterOuterAlt

-0.67

skosten

-0.65

 level

-0.64

setLevel

-0.63

ograma

-0.62

WISE

-0.60

entification

-0.60

ynchronously

-0.60

POSITIVE LOGITS

شهاد

0.61

 Ciò

0.54

 motion

0.52

 cantit

0.51

pruch

0.50

:+:

0.49

 religieuses

0.49

ształ

0.49

PRNewswire

0.49

 poveznice

0.45

Activations Density 0.353%

instances of words related to comparisons and relationships

No Comments

No Known Activations