INDEX

Explanations

words related to emotional states or reactions

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.03

2:0.08

3:0.06

4:0.14

5:0.14

6:0.04

7:0.05

8:0.15

9:0.08

10:0.07

11:0.03

Negative Logits

epad

-1.32

omer

-1.22

 steroid

-1.17

Jose

-1.16

 ingested

-1.15

ebus

-1.15

********************************

-1.13

pot

-1.13

ernels

-1.12

 Picks

-1.05

POSITIVE LOGITS

inen

1.23

 Excellence

1.19

inki

1.16

 Beaut

1.16

 Colleg

1.15

ische

1.14

ür

1.12

ë

1.11

��

1.11

ç

1.10

Activations Density 0.018%

words related to emotional states or reactions

No Comments

No Known Activations