INDEX

Explanations

warnings or alerts within a context

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

phrases indicating alerts or warnings regarding potential dangers or issues

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

1:0.03

2:0.15

3:0.10

4:0.01

5:0.03

6:0.06

7:0.15

8:0.10

9:0.14

10:0.06

11:0.11

Negative Logits

 Lois

-0.93

 forfeit

-0.93

�

-0.90

MIT

-0.89

ULAR

-0.89

fman

-0.85

 Minute

-0.82

lez

-0.82

lishes

-0.82

athon

-0.81

POSITIVE LOGITS

abies

1.18

ough

0.98

fur

0.94

unci

0.93

ipl

0.93

 repr

0.89

 hars

0.86

antly

0.86

 outbreaks

0.86

bugs

0.86

Activations Density 0.019%

warnings or alerts within a context

phrases indicating alerts or warnings regarding potential dangers or issues

No Comments

No Known Activations