INDEX

Explanations

terms related to scientific and historical credibility

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

1:0.02

2:0.06

3:0.12

4:0.03

5:0.05

6:0.15

7:0.28

8:0.04

9:0.03

10:0.08

11:0.06

Negative Logits

Interstitial

-1.31

EStreamFrame

-1.27

reau

-1.14

SHARE

-1.07

olina

-1.04

HUD

-1.03

��

-1.02

UX

-1.02

illes

-1.02

alone

-1.02

POSITIVE LOGITS

gypt

1.29

 cert

1.23

 debunk

1.23

sounding

1.18

 opinion

1.14

 Publication

1.13

 Helpful

1.08

smanship

1.07

sonian

1.07

 debunked

1.06

Activations Density 0.022%

terms related to scientific and historical credibility

No Comments

No Known Activations