INDEX

Explanations

phrases indicating doubt or uncertainty about events and outcomes

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.07

2:0.06

3:0.02

4:0.01

5:0.06

6:0.05

7:0.04

8:0.03

9:0.08

10:0.10

11:0.40

Negative Logits

 gist

-1.20

adder

-1.18

 assorted

-1.17

ortment

-1.16

itton

-1.12

LI

-1.12

oided

-1.11

ENGTH

-1.06

LAN

-1.04

 redes

-1.03

POSITIVE LOGITS

 anymore

3.72

nor

3.54

 whatsoever

2.38

nor

2.14

 necessarily

2.08

 slightest

2.08

yet

2.04

any

2.03

 anything

2.03

 anybody

1.96

Activations Density 1.202%

phrases indicating doubt or uncertainty about events and outcomes

No Comments

No Known Activations