INDEX

Explanations

names, places, and specific entities mentioned within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

+#+#

-0.99

fileID

-0.94

XmlAccessType

-0.93

mobileqq

-0.90

jsdelivr

-0.86

 autorytatywna

-0.85

CFP

-0.84

LikeLike

-0.83

Jegyzetek

-0.83

AndroidJUnit

-0.82

POSITIVE LOGITS

</b>

0.84

 Bock

0.84

 Siva

0.83

 Rade

0.81

Jax

0.79

 Helga

0.76

angelo

0.73

 Rath

0.72

hå

0.72

 Schwe

0.72

Activations Density 2.195%

names, places, and specific entities mentioned within the text

No Comments

No Known Activations