INDEX

Explanations

assertions regarding expectations and predictions

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

1:0.08

2:0.12

3:0.04

4:0.01

5:0.06

6:0.09

7:0.09

8:0.12

9:0.11

10:0.14

11:0.08

Negative Logits

allows

-0.88

utive

-0.88

ossal

-0.82

lier

-0.81

activated

-0.79

bush

-0.78

 reapp

-0.78

iosyncr

-0.77

uitive

-0.77

 Reneg

-0.77

POSITIVE LOGITS

��

1.22

''.

1.14

の�

1.05

IAN

0.99

ESSION

0.99

�

0.98

Quotes

0.95

TAG

0.95

EVA

0.94

HUD

0.94

Activations Density 0.390%

assertions regarding expectations and predictions

No Comments

No Known Activations