INDEX

Explanations

dissenting or contrasting viewpoints in statements

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

occurrences of commas in the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.01

1:0.02

2:0.09

3:0.03

4:0.02

5:0.03

6:0.11

7:0.11

8:0.08

9:0.25

10:0.04

11:0.17

Negative Logits

oreal

-1.31

FG

-1.24

rouse

-1.22

ivery

-1.19

Elk

-1.15

 Release

-1.15

scribe

-1.15

 Camel

-1.12

 Basketball

-1.11

SG

-1.09

POSITIVE LOGITS

uthor

1.28

EEK

1.28

stellar

1.21

weak

1.18

aspberry

1.17

 fortun

1.15

nil

1.15

 conclud

1.15

 Kund

1.14

theless

1.12

Activations Density 0.004%

dissenting or contrasting viewpoints in statements

occurrences of commas in the text

No Known Activations