INDEX

Explanations

attends to tokens that are marked as class members or methods by another token that appears later in the sequence

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

1:0.09

2:0.07

3:0.11

4:0.12

5:0.07

6:0.31

7:0.13

Negative Logits

yntaxException

-0.58

 ujednoznacz

-0.57

 MonoBehaviour

-0.53

 AssemblyTitle

-0.53

 виправивши

-0.50

 vPvB

-0.44

Gön

-0.44

 NSCoder

-0.44

IContainer

-0.43

 lenker

-0.42

POSITIVE LOGITS

0.31

0.29

↵

0.29

0.28

0.27

0.26

Activations Density 0.760%

attends to tokens that are marked as class members or methods by another token that appears later in the sequence

No Comments

No Known Activations