INDEX

Explanations

keywords that indicate separation or distinction between entities or concepts

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

1:0.03

2:0.05

3:0.03

4:0.02

5:0.04

6:0.03

7:0.04

8:0.07

9:0.44

10:0.05

11:0.13

Negative Logits

visor

-1.61

visors

-1.55

irin

-1.25

atl

-1.19

aware

-1.19

aya

-1.16

orc

-1.16

elist

-1.16

yssey

-1.16

装

-1.15

POSITIVE LOGITS

 chronological

1.31

 Codex

1.23

 fist

1.22

 realities

1.19

 evenly

1.17

 disparate

1.14

RTX

1.12

 physical

1.11

 dots

1.10

 Chemical

1.09

Activations Density 0.025%

keywords that indicate separation or distinction between entities or concepts

No Comments

No Known Activations