INDEX

Explanations

mentions of individual names and locations

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

details related to legal proceedings and medical conditions

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

1:0.09

2:0.14

3:0.05

4:0.01

5:0.04

6:0.09

7:0.09

8:0.10

9:0.15

10:0.11

11:0.07

Negative Logits

erity

-0.98

SPONSORED

-0.96

ecycle

-0.94

ankind

-0.93

ilee

-0.89

Magikarp

-0.84

 perpet

-0.84

ombat

-0.83

 Awareness

-0.83

iferation

-0.82

POSITIVE LOGITS

�士

1.00

zzo

0.89

robe

0.88

ーテ

0.87

papers

0.85

れ

0.81

ILS

0.80

 injure

0.80

aram

0.80

jew

0.79

Activations Density 0.208%

mentions of individual names and locations

details related to legal proceedings and medical conditions

No Comments

No Known Activations