INDEX

Explanations

terms related to categories and classifications in scientific research

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SuccessListener

-0.74

'])){

-0.67

ruptedException

-0.65

cplusplus

-0.65

 RestTemplate

-0.64

로그램

-0.63

größern

-0.62

:))

-0.60

URLException

-0.60

!!!)

-0.59

POSITIVE LOGITS

 pseudo

0.80

geo

0.76

0.75

Pseudo

0.72

multi

0.72

 anti

0.72

 micro

0.71

 Counter

0.71

Multi

0.70

 multi

0.70

Activations Density 1.301%

terms related to categories and classifications in scientific research

No Comments

No Known Activations