INDEX

Explanations

quantitative data and numerical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 resourceCulture

-0.96

 كومونز

-0.95

 дописавши

-0.93

 виправивши

-0.91

 Chwiliwch

-0.91

 للاسماء

-0.87

complexContent

-0.87

featureID

-0.86

 Wikimedijinoj

-0.86

 ProtoMessage

-0.85

POSITIVE LOGITS

0.51

__

0.47

PR

0.45

0.44

SY

0.43

main

0.41

↵

0.40

sw

0.40

0.38

Activations Density 0.075%

quantitative data and numerical representations

No Comments

No Known Activations