INDEX

Explanations

attends to tokens marked as "to" or "is" from contextually relevant tokens marked with double square brackets

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

0:0.02

1:0.07

2:0.26

3:0.10

4:0.05

5:0.14

6:0.19

7:0.12

Negative Logits

-0.90

in

-0.86

on

-0.86

-0.85

-0.84

to

-0.83

POSITIVE LOGITS

"]);

1.54

"])

1.48

"]

1.46

'));

1.45

'){

1.45

']);

1.43

")){

1.43

"],

1.41

')):

1.41

"];

1.40

Activations Density 0.188%

attends to tokens marked as "to" or "is" from contextually relevant tokens marked with double square brackets

No Comments

No Known Activations