INDEX

Explanations

questions related to legal proceedings

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

phrases indicating the outcome of situations or events

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

1:0.02

2:0.05

3:0.23

4:0.01

5:0.03

6:0.06

7:0.19

8:0.05

9:0.06

10:0.06

11:0.16

Negative Logits

osponsors

-1.21

Cola

-1.20

angelo

-1.16

udd

-1.14

 shelves

-1.12

bors

-1.11

Lat

-1.11

REF

-1.09

 attic

-1.07

okingly

-1.06

POSITIVE LOGITS

 outcome

1.25

 outcomes

1.17

 outweigh

1.16

 evaluations

1.09

nation

1.07

 happ

1.07

bye

1.06

lihood

1.06

 depends

1.05

 calculation

1.05

Activations Density 0.004%

questions related to legal proceedings

phrases indicating the outcome of situations or events

No Comments

No Known Activations