INDEX

Explanations

references to specific segments in a medical or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

WithIOException

-0.80

 nahilalakip

-0.79

 MainAxisSize

-0.77

########.

-0.72

RTEE

-0.71

&[

-0.69

oredCriteria

-0.68

contentLoaded

-0.65

 INCLUD

-0.65

 المعيارى

-0.63

POSITIVE LOGITS

segments

0.68

 segments

0.66

 channels

0.63

Within

0.62

Ratio

0.61

Efficiency

0.61

 Within

0.60

 channel

0.60

efficient

0.59

 Channels

0.58

Activations Density 0.173%

references to specific segments in a medical or technical context

No Comments

No Known Activations