INDEX

Explanations

references to specific individuals, particularly those with the name "Brad."

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

0:0.01

1:0.03

2:0.09

3:0.25

4:0.02

5:0.02

6:0.14

7:0.13

8:0.04

9:0.07

10:0.07

11:0.08

Negative Logits

 Juliet

-1.06

 Reps

-1.06

PRES

-1.06

guards

-1.04

�

-1.04

 SPORTS

-1.03

 composition

-0.99

gov

-0.98

ModLoader

-0.98

ATURE

-0.97

POSITIVE LOGITS

ylon

1.28

ussen

1.18

rane

1.10

illet

1.07

oling

1.06

DOS

1.01

 Secondary

1.00

plings

1.00

enture

1.00

rive

0.98

Activations Density 0.006%

references to specific individuals, particularly those with the name "Brad."

No Comments

No Known Activations