INDEX

Explanations

phrases indicating falsehoods or exaggerations

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_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

0:0.07

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.06

9:0.09

10:0.10

11:0.07

Negative Logits

IER

-2.29

TT

-2.23

Dou

-2.23

assetsadobe

-2.14

�

-2.13

LB

-2.03

rieg

-2.01

uy

-2.00

guy

-1.97

POSITIVE LOGITS

 subdued

2.15

 adherent

2.14

 flesh

2.12

 immunity

2.10

 hospitality

2.08

ariat

2.06

 heartbeat

2.02

 accompanying

2.00

vation

1.99

ana

1.98

Activations Density 0.000%

phrases indicating falsehoods or exaggerations

No Comments

No Known Activations