INDEX

Explanations

concepts related to deeper cognitive reflection or introspection

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

0:0.05

1:0.05

2:0.15

3:0.13

4:0.08

5:0.07

6:0.05

7:0.08

8:0.06

9:0.06

10:0.08

11:0.08

Negative Logits

 verified

-1.68

 reopened

-1.67

 uncovered

-1.56

 sporadic

-1.52

 sighting

-1.50

 sightings

-1.49

 finalized

-1.49

 publication

-1.44

 reopen

-1.44

interrupted

-1.42

POSITIVE LOGITS

monary

1.64

arat

1.63

illac

1.56

abba

1.50

aeda

1.50

ahime

1.50

zbollah

1.48

tro

1.43

inav

1.37

doms

1.34

Activations Density 0.000%

concepts related to deeper cognitive reflection or introspection

No Comments

No Known Activations