INDEX

Explanations

verbs indicating actions or intentions

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

words and phrases that convey sentiments of surprise, emotion, and various states of being

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

0:0.01

1:0.05

2:0.18

3:0.03

4:0.01

5:0.07

6:0.13

7:0.08

8:0.10

9:0.15

10:0.08

11:0.05

Negative Logits

utations

-1.04

 respectively

-1.03

 comprises

-1.02

 apiece

-0.98

 appearances

-0.96

 slots

-0.94

 divides

-0.92

 substrate

-0.91

 allowances

-0.91

 tarn

-0.90

POSITIVE LOGITS

 myself

1.40

 happiest

1.29

poke

1.12

EStream

1.11

 laughing

1.08

itialized

1.07

 yesterday

1.06

acted

1.06

 サーティワン

1.06

sighted

1.05

Activations Density 0.093%

verbs indicating actions or intentions

words and phrases that convey sentiments of surprise, emotion, and various states of being

No Comments

No Known Activations