INDEX

Explanations

phrases related to career paths and rights

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_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

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.08

3:0.06

4:0.14

5:0.02

6:0.10

7:0.32

8:0.04

9:0.04

10:0.07

11:0.04

Negative Logits

toggle

-1.69

requency

-1.65

laughter

-1.54

dra

-1.51

QUI

-1.48

<<

-1.48

 firsthand

-1.48

acted

-1.41

acting

-1.39

oğan

-1.36

POSITIVE LOGITS

 virginity

2.07

 allegiance

2.04

wart

1.76

 portfolios

1.67

warts

1.65

 loyalty

1.61

 excellence

1.58

 correctness

1.56

Downloadha

1.55

ership

1.54

Activations Density 0.001%

phrases related to career paths and rights

No Comments

No Known Activations