INDEX

Explanations

repeated conjunctions and connectors in sentences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

conjunctions and phrases indicating connection or addition in sentences

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

0:0.04

1:0.03

2:0.06

3:0.11

4:0.06

5:0.08

6:0.06

7:0.09

8:0.20

9:0.07

10:0.11

11:0.06

Negative Logits

autions

-1.27

erity

-1.22

 humane

-1.14

 Helpful

-1.10

 scient

-1.05

 stupid

-1.05

 morals

-1.05

].

-1.05

 goddamn

-1.05

��

-1.03

POSITIVE LOGITS

umn

1.33

lag

1.28

ammy

1.18

tein

1.15

arthed

1.14

ranch

1.12

 respectively

1.11

 Belg

1.09

ansen

1.08

AMS

1.08

Activations Density 0.034%

repeated conjunctions and connectors in sentences

conjunctions and phrases indicating connection or addition in sentences

No Known Activations

repeated conjunctions and connectors in sentences

conjunctions and phrases indicating connection or addition in sentences

No Known Activations