INDEX

Explanations

attends to specialized or scientific terms from more general terms providing context about those specialized terms

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

1:0.11

2:0.47

3:0.09

4:0.05

5:0.06

6:0.07

7:0.08

Negative Logits

 myſelf

-3.17

Efq

-3.13

 itſelf

-3.03

^(@)

-3.03

 Theſe

-2.83

 Monfieur

-2.83

 Jefus

-2.72

BibitemShut

-2.70

 ―――――

-2.69

ſelves

-2.67

POSITIVE LOGITS

1.71

1.62

1.61

1.55

↵

1.48

1.46

1.45

1.44

1.41

Activations Density 0.237%

attends to specialized or scientific terms from more general terms providing context about those specialized terms

No Comments

No Known Activations