INDEX

Explanations

phrases indicating a call to action or taking a moment to reflect

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

0:0.03

1:0.02

2:0.13

3:0.07

4:0.13

5:0.03

6:0.03

7:0.28

8:0.04

9:0.04

10:0.06

11:0.08

Negative Logits

geries

-1.75

acious

-1.51

ategories

-1.50

adoes

-1.48

 heights

-1.47

;;;;;;;;;;;;

-1.47

amation

-1.41

 Craw

-1.41

 Hels

-1.37

packing

-1.36

POSITIVE LOGITS

 goodbye

1.82

 thanking

1.62

 reminis

1.58

 acknowledging

1.55

 reverence

1.45

 remembering

1.42

 remembered

1.42

 mourning

1.41

 regret

1.37

 solemn

1.35

Activations Density 0.002%

phrases indicating a call to action or taking a moment to reflect

No Comments

No Known Activations