INDEX

Explanations

phrases indicating comparisons and relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

止

-0.47

misc

-0.45

ji

-0.44

áról

-0.42

ember

-0.41

-0.40

ForEach

-0.40

om

-0.40

Barton

-0.40

 Historically

-0.39

POSITIVE LOGITS

 CreateTagHelper

1.04

GOTREF

1.02

migrationBuilder

0.90

 InputDecoration

0.88

 defaultstate

0.86

RectangleBorder

0.86

 AssemblyCulture

0.83

 EconPapers

0.82

AddTagHelper

0.80

 насељу

0.78

Activations Density 0.368%

phrases indicating comparisons and relationships

No Comments

No Known Activations