INDEX

Explanations

phrases that describe methods or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ContentLoaded

-0.66

AddWithValue

-0.60

@[

-0.60

merzen

-0.55

etree

-0.54

lucene

-0.53

adhé

-0.53

ület

-0.52

örté

-0.52

ribut

-0.52

POSITIVE LOGITS

 Böyle

0.84

 Así

0.80

 näin

0.79

Así

0.77

Così

0.73

 Così

0.71

τσι

0.70

 Weise

0.69

 así

0.68

Так

0.67

Activations Density 0.190%

phrases that describe methods or processes

No Comments

No Known Activations