INDEX

Explanations

words related to physical locations or references to "in."

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

0:0.09

1:0.02

2:0.08

3:0.05

4:0.13

5:0.13

6:0.03

7:0.02

8:0.16

9:0.16

10:0.06

11:0.02

Negative Logits

 suspic

-1.30

 traged

-1.21

 Seym

-1.08

 enthusi

-1.06

 hail

-1.02

ideos

-1.00

wcs

-0.99

 conscientious

-0.97

icter

-0.96

 distur

-0.96

POSITIVE LOGITS

ahime

1.35

ryu

1.31

etus

1.19

usters

1.12

 ling

1.11

tein

1.11

gram

1.10

hod

1.09

iao

1.08

istics

1.06

Activations Density 0.047%

words related to physical locations or references to "in."

No Comments

No Known Activations