INDEX

Explanations

attends to the return token associated with a new instance from various function calls across different contexts

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.14

2:0.10

3:0.06

4:0.06

5:0.04

6:0.09

7:0.32

Negative Logits

 "..\..\

-0.33

 Réponses

-0.33

ніципалі

-0.32

ViewFeatures

-0.31

Pyx

-0.29

はじめに

-0.28

HomeAsUpEnabled

-0.28

참고

-0.28

/*

-0.27

rrggbb

-0.27

POSITIVE LOGITS

haden

0.33

 للاسماء

0.29

เลข

0.29

oflavin

0.28

modellen

0.28

ficulty

0.28

ftance

0.26

 initWithFrame

0.26

thmetic

0.26

strokeStyle

0.26

Activations Density 0.161%

attends to the return token associated with a new instance from various function calls across different contexts

No Comments

No Known Activations