INDEX

Explanations

technical identifiers and terms related to programming and statistical functions

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

RepeatedField

-0.70

 Merz

-0.67

vičius

-0.66

 pescoço

-0.63

paddingVertical

-0.62

SearchParams

-0.62

kawi

-0.62

ŚCI

-0.62

 Bellini

-0.61

 Palmeiras

-0.61

POSITIVE LOGITS

 Socorro

0.98

SOP

0.92

onto

0.91

omo

0.91

bof

0.90

ACO

0.90

 woll

0.89

 Soro

0.88

Jod

0.88

 poro

0.88

Activations Density 6.990%

technical identifiers and terms related to programming and statistical functions

No Comments

No Known Activations