INDEX

Explanations

attends to quotes from arbitrary mentions of subsequent 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

1:0.04

2:0.55

3:0.09

4:0.03

5:0.05

6:0.12

7:0.08

Negative Logits

’

-0.91

“

-0.90

-0.80

<strong>

-0.80

”

-0.80

<eos>

-0.79

-0.78

-0.77

POSITIVE LOGITS

 myſelf

1.65

Efq

1.62

 itſelf

1.58

 Theſe

1.56

 Jefus

1.48

 Monfieur

1.47

 ―――――

1.46

 purpoſe

1.46

^(@)

1.44

ſelves

1.41

Activations Density 0.643%

attends to quotes from arbitrary mentions of subsequent tokens

No Comments

No Known Activations