INDEX

Explanations

attends to the token "uint" from related code tokens, specifically focusing on data types and function arguments

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

0:0.01

1:0.02

2:0.05

3:0.38

4:0.05

5:0.06

6:0.33

7:0.05

Negative Logits

 myſelf

-1.41

 itſelf

-1.39

 pleaſure

-1.37

Efq

-1.27

 purpoſe

-1.24

 raiſ

-1.23

 Theſe

-1.23

 Jefus

-1.21

 ſche

-1.20

 Majefty

-1.20

POSITIVE LOGITS

<eos>

0.73

0.69

↵

0.68

0.58

0.57

0.55

...

0.51

of

0.50

to

0.50

Activations Density 0.206%

attends to the token "uint" from related code tokens, specifically focusing on data types and function arguments

No Comments

No Known Activations