INDEX

Explanations

references to specific hurricanes and their impacts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.03

1:0.04

2:0.08

3:0.08

4:0.02

5:0.03

6:0.14

7:0.19

8:0.07

9:0.04

10:0.11

11:0.12

Negative Logits

acebook

-1.01

ENSE

-0.99

IENT

-0.99

puter

-0.97

UTE

-0.94

ozo

-0.93

ACTION

-0.93

ildo

-0.92

iltr

-0.92

construct

-0.92

POSITIVE LOGITS

ascus

1.24

liner

1.15

winter

1.11

helm

1.02

 Blizz

0.99

 Sandy

0.92

 liner

0.92

vati

0.89

wid

0.88

 Kemp

0.87

Activations Density 0.018%

references to specific hurricanes and their impacts

No Comments

No Known Activations