INDEX

Explanations

words associated with quantities or measurements

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

0:0.02

1:0.06

2:0.12

3:0.04

4:0.02

5:0.08

6:0.12

7:0.07

8:0.13

9:0.11

10:0.08

11:0.08

Negative Logits

��

-1.46

DCS

-1.02

ⓘ

-1.01

OULD

-1.00

Self

-0.94

。

-0.93

]=

-0.93

externalActionCode

-0.91

 ours

-0.90

 unsuspecting

-0.89

POSITIVE LOGITS

been

1.27

ortium

1.23

 meanwhile

1.16

tein

1.16

 extensively

1.07

bara

1.05

aciously

1.05

 recently

1.05

ilial

1.03

 moreover

1.01

Activations Density 0.282%

words associated with quantities or measurements

No Comments

No Known Activations