INDEX

Explanations

action verbs in the present tense

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

phrases indicating effective actions or strategies in various contexts

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

2:0.09

3:0.04

4:0.02

5:0.04

6:0.07

7:0.08

8:0.04

9:0.15

10:0.07

11:0.28

Negative Logits

authors

-1.22

 astroph

-1.17

pleasant

-1.14

 affili

-1.12

 pilgrims

-1.09

 inclined

-1.08

 richness

-1.06

initely

-1.06

 optionally

-1.05

requent

-1.05

POSITIVE LOGITS

-+-+

1.33

\\\\\\\\

1.26

Effective

1.21

 Craigslist

1.13

xit

1.12

�醒

1.11

quez

1.10

OPA

1.09

lift

1.07

ガ

1.07

Activations Density 0.015%

action verbs in the present tense

phrases indicating effective actions or strategies in various contexts

No Comments

No Known Activations