INDEX

Explanations

attends to the "github" token from the paired "github" token

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

0:0.04

1:0.57

2:0.10

3:0.04

4:0.06

5:0.05

6:0.06

7:0.05

Negative Logits

-0.35

-0.31

↵

-0.30

-0.29

msub

-0.28

-0.27

and

-0.27

POSITIVE LOGITS

 itſelf

0.49

'}>

0.42

}.

0.42

contentLoaded

0.41

"):

0.40

>");

0.40

 ་་

0.40

}]

0.40

]:

0.40

Activations Density 0.007%

attends to the "github" token from the paired "github" token

No Comments

No Known Activations