INDEX

Explanations

attends to tokens marking an apostrophe from tokens marking a quotation

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

0:0.03

1:0.15

2:0.34

3:0.05

4:0.06

5:0.08

6:0.08

7:0.16

Negative Logits

^(@)

-1.48

BibitemShut

-1.47

)");

-1.47

"])

-1.46

"):

-1.46

 Мексичка

-1.45

"]

-1.41

)";

-1.41

"],

-1.40

")));

-1.40

POSITIVE LOGITS

1.03

0.98

0.93

0.91

is

0.90

and

0.90

Activations Density 0.049%

attends to tokens marking an apostrophe from tokens marking a quotation

No Comments

No Known Activations