INDEX

Explanations

comparative phrases discussing performance differences and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

Џ

-0.47

 ilan

-0.43

weif

-0.42

zaron

-0.41

kopp

-0.40

はじめて

-0.39

var

-0.39

初めて

-0.39

ieť

-0.39

otel

-0.38

POSITIVE LOGITS

 CreateTagHelper

0.89

DockStyle

0.84

 lenker

0.83

VersionUID

0.78

AndEndTag

0.74

enterOuterAlt

0.69

GEBURTSDATUM

0.69

Rujuakan

0.68

 createSlice

0.68

WebElementEntity

0.67

Activations Density 0.588%

comparative phrases discussing performance differences and values

No Comments

No Known Activations