INDEX

Explanations

phrases indicating pretense or impersonation

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

0:0.01

1:0.04

2:0.07

3:0.14

4:0.02

5:0.03

6:0.04

7:0.07

8:0.08

9:0.22

10:0.06

11:0.14

Negative Logits

ilst

-2.22

requires

-1.35

ourses

-1.23

sections

-1.20

ichever

-1.16

arger

-1.15

ests

-1.14

hens

-1.14

Detailed

-1.12

alon

-1.11

POSITIVE LOGITS

 nostalg

1.36

 Clown

1.22

 imitation

1.20

false

1.18

 pretend

1.15

 innocence

1.14

 Duck

1.13

 Godd

1.11

 pretended

1.10

cav

1.09

Activations Density 0.014%

phrases indicating pretense or impersonation

No Comments

No Known Activations