INDEX

Explanations

attends to the token "NS" from instances of "NS" in various programming contexts

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

0:0.03

1:0.47

2:0.17

3:0.03

4:0.06

5:0.05

6:0.03

7:0.11

Negative Logits

-0.54

-0.48

-0.40

-0.39

-0.38

-0.37

-0.36

POSITIVE LOGITS

parsedMessage

0.91

GEBURTSDATUM

0.79

abestanden

0.78

 '\\;'

0.75

ագրություններ

0.73

^(@)

0.73

NUMX

0.73

'},

0.73

findpost

0.72

providedIn

0.71

Activations Density 0.028%

attends to the token "NS" from instances of "NS" in various programming contexts

No Comments

No Known Activations