INDEX

Explanations

attends from conditional tokens to return tokens

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.02

2:0.05

3:0.56

4:0.02

5:0.04

6:0.15

7:0.10

Negative Logits

setVerticalGroup

-0.47

+#+#

-0.45

 bezeichneter

-0.44

AutoresizingMask

-0.44

sidemargin

-0.43

 متعلقه

-0.42

DockStyle

-0.41

CloseOperation

-0.41

tagHelperRunner

-0.41

 архивлан

-0.41

POSITIVE LOGITS

 both

0.23

0.22

 multi

0.22

</b>

0.21

in

0.21

le

0.21

The

0.21

Activations Density 0.176%

attends from conditional tokens to return tokens

No Comments

No Known Activations