INDEX

Explanations

attends to tokens indicating a state, condition, or place from tokens referencing a related time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

0:0.06

1:0.02

2:0.02

3:0.02

4:0.18

5:0.61

6:0.02

7:0.04

Negative Logits

-0.35

回

-0.29

www

-0.29

<eos>

-0.28

ary

-0.28

求

-0.28

、

-0.27

://

-0.27

ine

-0.26

POSITIVE LOGITS

̈́

0.46

^(@)

0.44

PYX

0.43

 Majefty

0.42

CloseOperation

0.42

UseVisualStyle

0.42

 незавершена

0.40

 auffi

0.40

ſelf

0.40

HtmlAttribute

0.39

Activations Density 0.936%

attends to tokens indicating a state, condition, or place from tokens referencing a related time

No Comments

No Known Activations