INDEX

Explanations

words related to changes or developments happening in different contexts, such as economy, society, or personal beliefs

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

references to societal issues and concerns, particularly in relation to justice and economic conditions

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

1:0.04

2:0.13

3:0.08

4:0.02

5:0.03

6:0.06

7:0.13

8:0.15

9:0.14

10:0.06

11:0.08

Negative Logits

pps

-1.29

anu

-1.19

isan

-1.09

alk

-1.07

bors

-1.05

lde

-1.04

ynt

-1.02

anc

-1.02

rican

-0.98

aned

-0.97

POSITIVE LOGITS

 discussions

1.06

soType

1.04

 momentum

1.04

 unbeliev

1.00

 effic

0.99

覚醒

0.98

 reperto

0.97

 defe

0.96

rawdownloadcloneembedreportprint

0.96

 ILCS

0.96

Activations Density 0.028%

words related to changes or developments happening in different contexts, such as economy, society, or personal beliefs

references to societal issues and concerns, particularly in relation to justice and economic conditions

No Known Activations