INDEX

Explanations

frequent occurrences of Vietnamese pronunciation and phonetic patterns

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.02

2:0.16

3:0.08

4:0.17

5:0.11

6:0.03

7:0.03

8:0.08

9:0.07

10:0.08

11:0.04

Negative Logits

 hive

-1.13

 agre

-1.06

 satell

-1.05

 clam

-1.05

church

-1.01

DOS

-1.00

market

-0.98

 Lauder

-0.97

 enthusi

-0.95

 bidder

-0.95

POSITIVE LOGITS

 Receiver

1.32

VT

1.16

ć

1.16

sson

1.15

️

1.14

�

1.10

yo

1.08

 Coverage

1.07

itars

1.01

ה

0.99

Activations Density 0.008%

frequent occurrences of Vietnamese pronunciation and phonetic patterns

No Comments

No Known Activations