INDEX

Explanations

attends to the token "talk" from various "about" 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.04

2:0.03

3:0.02

4:0.17

5:0.59

6:0.03

7:0.03

Negative Logits

出版年

-0.74

IsContent

-0.71

 InputDecoration

-0.68

 EconPapers

-0.67

 مرئيه

-0.66

 שוליים

-0.63

Efq

-0.63

\{\\

-0.62

 مشين

-0.61

httphttps

-0.60

POSITIVE LOGITS

0.37

0.34

0.33

<eos>

0.29

0.28

and

0.28

de

0.27

Activations Density 0.028%

attends to the token "talk" from various "about" tokens

No Comments

No Known Activations