INDEX

Explanations

items and categories in lists or enumerations

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.02

2:0.10

3:0.09

4:0.06

5:0.07

6:0.04

7:0.03

8:0.27

9:0.10

10:0.07

11:0.03

Negative Logits

peat

-1.20

��

-1.16

ð

-1.16

 GOODMAN

-1.12

entimes

-1.08

�

-1.08

lance

-1.07

án

-1.07

inition

-1.05

onga

-1.03

POSITIVE LOGITS

 裏�

1.14

ackets

1.09

bleacher

1.09

Pog

1.08

 addresses

1.08

 voic

1.06

"(

1.05

 pros

1.05

oples

1.04

 Pros

1.03

Activations Density 0.023%

items and categories in lists or enumerations

No Comments

No Known Activations