INDEX

Explanations

occurrences of numerical values, especially in the context of scientific and technical data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

FL

-0.55

Fro

-0.53

InjectAttribute

-0.53

WF

-0.52

FontAwesome

-0.50

 Frankfort

-0.49

Autowired

-0.48

orescence

-0.47

WF

-0.46

PW

-0.46

POSITIVE LOGITS

AsUp

0.72

✭✭

0.69

Ayu

0.69

principalTable

0.69

onAttach

0.68

hoga

0.68

 manslaughter

0.67

rawDesc

0.66

ESTAMP

0.64

iços

0.64

Activations Density 0.493%

occurrences of numerical values, especially in the context of scientific and technical data

No Comments

No Known Activations