INDEX

Explanations

attends to specific technical or academic terms from general references or identifiable names

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

0:0.05

1:0.02

2:0.04

3:0.02

4:0.20

5:0.59

6:0.02

7:0.03

Negative Logits

 Monfieur

-0.60

 kasarigan

-0.56

 itſelf

-0.54

parsedMessage

-0.53

.";

-0.52

 Jefus

-0.52

ftagPool

-0.52

 Theſe

-0.51

Efq

-0.50

 صوتيه

-0.50

POSITIVE LOGITS

0.48

0.41

0.40

0.37

0.36

0.34

0.33

Activations Density 1.263%

attends to specific technical or academic terms from general references or identifiable names

No Comments

No Known Activations