INDEX

Explanations

phrases related to unity and collective goals

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

0:0.04

1:0.01

2:0.11

3:0.06

4:0.16

5:0.03

6:0.04

7:0.28

8:0.04

9:0.05

10:0.08

11:0.05

Negative Logits

izens

-1.69

 interns

-1.67

 applicants

-1.55

 tenure

-1.48

ifier

-1.47

ify

-1.45

 freshman

-1.44

 reviewers

-1.42

 junior

-1.41

 workplaces

-1.39

POSITIVE LOGITS

 hugs

2.02

isse

1.67

rang

1.62

},"

1.60

MpServer

1.58

amph

1.54

united

1.51

 embraces

1.50

drawn

1.49

none

1.48

Activations Density 0.001%

phrases related to unity and collective goals

No Comments

No Known Activations