INDEX

Explanations

references to individuals and their connections in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Pay

-0.56

pay

-0.48

いる

-0.46

넷

-0.46

Pay

-0.46

ia

-0.45

umer

-0.44

tua

-0.44

Do

-0.43

DO

-0.43

POSITIVE LOGITS

TagMode

1.14

 فريبيس

1.13

IGraphics

1.10

AndEndTag

1.08

RenderAtEndOf

1.04

 متعلقه

1.00

AutoScaleMode

0.98

 jakie

0.98

Hauptartikel

0.97

'{@

0.97

Activations Density 0.263%

references to individuals and their connections in a narrative context

No Comments

No Known Activations