INDEX

Explanations

attends to mathematical expression tokens from preceding tokens

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

1:0.03

2:0.61

3:0.06

4:0.05

5:0.05

6:0.09

7:0.05

Negative Logits

-3.59

-3.27

-2.98

<eos>

-2.95

-2.81

↵↵

-2.77

↵

-2.77

in

-2.72

-2.67

-2.66

POSITIVE LOGITS

 myſelf

7.19

 itſelf

6.88

Efq

6.81

 Monfieur

6.63

 Theſe

6.25

 Jefus

6.22

 Majefty

6.13

 purpoſe

6.09

 pleaſure

6.09

 themſelves

6.00

Activations Density 1.518%

attends to mathematical expression tokens from preceding tokens

No Comments

No Known Activations