INDEX

Explanations

concerns and risks related to health and safety

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_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

1:0.01

2:0.06

3:0.06

4:0.10

5:0.02

6:0.04

7:0.40

8:0.02

9:0.02

10:0.12

11:0.08

Negative Logits

cles

-1.73

endars

-1.65

FontSize

-1.63

Clar

-1.51

ele

-1.46

minus

-1.46

GRE

-1.44

Instance

-1.43

isec

-1.42

appointed

-1.40

POSITIVE LOGITS

 risk

2.15

 vulnerability

2.14

 jeopard

2.05

 harm

2.01

 risks

1.97

 unprotected

1.97

 risking

1.94

 endanger

1.82

 transmitting

1.80

 leakage

1.79

Activations Density 0.035%

concerns and risks related to health and safety

No Comments

No Known Activations