INDEX

Explanations

words related to misleading narratives and sensationalism in news or discourse

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

0:0.03

1:0.04

2:0.08

3:0.20

4:0.03

5:0.02

6:0.12

7:0.11

8:0.04

9:0.08

10:0.08

11:0.11

Negative Logits

omething

-1.25

 predec

-1.18

ngth

-1.17

 Wonders

-1.13

ortium

-1.11

 disadvant

-1.10

htaking

-0.97

athed

-0.97

cedented

-0.95

AAF

-0.94

POSITIVE LOGITS

�

1.10

perty

1.00

 argument

0.97

ody

0.96

 Isaac

0.94

�

0.94

java

0.90

Ly

0.89

ة

0.89

 Chicken

0.88

Activations Density 0.001%

words related to misleading narratives and sensationalism in news or discourse

No Comments

No Known Activations