INDEX

Explanations

phrases related to conversations or social interactions, particularly those that include action words

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.03

1:0.02

2:0.08

3:0.06

4:0.14

5:0.03

6:0.04

7:0.37

8:0.03

9:0.04

10:0.07

11:0.04

Negative Logits

ヘ

-2.06

save

-1.80

pez

-1.71

insured

-1.68

pg

-1.65

geons

-1.65

keys

-1.64

imester

-1.64

externalActionCode

-1.59

zed

-1.58

POSITIVE LOGITS

 inconsistencies

2.19

 discrepancies

1.95

 hypotheses

1.85

 flaws

1.81

 contradictory

1.79

 suspicion

1.79

 suspicious

1.78

 spurious

1.78

 theories

1.76

 inconsistency

1.74

Activations Density 0.000%

phrases related to conversations or social interactions, particularly those that include action words

No Known Activations