INDEX

Explanations

technical terms related to data security and disc golf maneuvers

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

terms related to complex systems and their operational mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.05

1:0.05

2:0.10

3:0.04

4:0.06

5:0.07

6:0.10

7:0.14

8:0.13

9:0.03

10:0.11

11:0.06

Negative Logits

azeera

-1.11

nian

-1.04

�

-0.99

い

-0.93

pixel

-0.93

sbm

-0.92

�

-0.92

ideo

-0.92

ipedia

-0.91

dfx

-0.90

POSITIVE LOGITS

LTD

1.00

 Enhancement

0.99

 Prom

0.97

 Featuring

0.95

 Volume

0.95

 Limited

0.93

 chaired

0.89

 specializes

0.87

 Outs

0.86

 Ambassador

0.85

Activations Density 0.780%

technical terms related to data security and disc golf maneuvers

terms related to complex systems and their operational mechanisms

No Comments

No Known Activations