INDEX

Explanations

terms related to hidden elements or configurations 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personensuche

-1.08

principalColumn

-1.06

ChildScrollView

-0.99

Rhestr

-0.97

 مواليد

-0.81

mybatisplus

-0.80

 désolés

-0.80

-0.79

MessageTagHelper

-0.79

/*---

-0.77

POSITIVE LOGITS

 hidden

1.06

 Hidden

1.05

Hidden

1.04

hidden

1.02

HIDDEN

0.77

 скры

0.65

隠

0.63

HID

0.58

隐藏

0.55

 concealed

0.53

Activations Density 0.011%

terms related to hidden elements or configurations in a context

No Comments

No Known Activations