INDEX

Explanations

attends to the "hide" token from various tokens denoting locations or contexts for hiding

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

0:0.62

1:0.01

2:0.02

3:0.02

4:0.17

5:0.07

6:0.01

7:0.04

Negative Logits

-0.37

-0.35

up

-0.34

-0.33

POSITIVE LOGITS

)");

0.67

^(@)

0.61

")));

0.60

>");

0.60

"):

0.59

>\<^

0.58

`,

0.55

'));

0.54

'):

0.54

."));

0.52

Activations Density 0.004%

attends to the "hide" token from various tokens denoting locations or contexts for hiding

No Comments

No Known Activations