INDEX

Explanations

variables representing parameters, specifically those denoted by 'tau'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__':

-0.75

wijl

-0.66

ymce

-0.65

Ley

-0.64

 Bergh

-0.61

 blessé

-0.60

ופת

-0.59

edia

-0.59

 Noth

-0.59

prest

-0.58

POSITIVE LOGITS

tau

2.74

tau

2.18

Tau

2.02

Tau

2.01

τ

1.65

τ

1.61



1.09

 taus

1.08

𝜏

1.05

taus

1.05

Activations Density 0.154%

variables representing parameters, specifically those denoted by 'tau'

No Comments

No Known Activations