INDEX

Explanations

detailed descriptions or explanations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases that express frequency and repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

0:0.12

1:0.04

2:0.08

3:0.17

4:0.04

5:0.07

6:0.07

7:0.05

8:0.05

9:0.06

10:0.14

11:0.06

Negative Logits

iere

-1.13

 Keller

-1.11

ELY

-1.10

VK

-1.09

ALS

-1.09

 spiked

-1.08

adj

-1.08

 tongues

-1.08

ILS

-1.07

 strongly

-1.07

POSITIVE LOGITS

 Droid

1.34

 imaginable

1.25

estial

1.23

�

1.20

imentary

1.18

ishable

1.15

 ripple

1.14

 ounce

1.11

except

1.11

 Mahjong

1.11

Activations Density 0.066%

detailed descriptions or explanations

phrases that express frequency and repetition

No Comments

No Known Activations