INDEX

Explanations

information related to academic research and achievements

oai_token-act-pair · gpt-3.5-turbo 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.03

2:0.10

3:0.19

4:0.03

5:0.10

6:0.08

7:0.03

8:0.11

9:0.09

10:0.08

11:0.03

Negative Logits

azard

-1.17

aples

-1.13

itaire

-1.10

 guiName

-1.06

ilaterally

-1.06

areth

-1.02

orks

-1.01

thora

-1.00

agate

-1.00

esters

-1.00

POSITIVE LOGITS

 counterpart

1.39

 counterparts

1.29

 companion

1.21

 consisted

1.14

 namesake

1.11

 superiors

1.11

 predecessors

1.08

 niece

1.06

 cousin

1.06

 exploits

1.06

Activations Density 0.182%

information related to academic research and achievements

No Comments

No Known Activations