INDEX

Explanations

references to direct emotional responses or sentiments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.04

2:0.10

3:0.06

4:0.02

5:0.06

6:0.09

7:0.13

8:0.11

9:0.05

10:0.09

11:0.18

Negative Logits

milo

-1.10

ulu

-1.10

immune

-1.10

ea

-1.09

assadors

-1.08

cill

-1.07

grand

-1.06

million

-1.06

′

-1.03

landers

-1.03

POSITIVE LOGITS

 Subtle

1.22

 arrang

1.21

 Than

1.14

than

1.05

 than

1.00

 Schne

0.99

 reven

0.99

 Shank

0.96

sts

0.96

jri

0.96

Activations Density 0.054%

references to direct emotional responses or sentiments

No Comments

No Known Activations