INDEX

Explanations

phrases related to public policies and governmental actions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases related to assessments and evaluations of standards, particularly in the context of educational or institutional performance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

0:0.03

1:0.08

2:0.11

3:0.02

4:0.04

5:0.12

6:0.11

7:0.10

8:0.09

9:0.07

10:0.11

11:0.06

Negative Logits

ツ

-1.26

ビ

-1.25

-1.23

wcsstore

-1.23

い

-1.21

ギ

-1.20

ナ

-1.13

umbn

-1.12

boro

-1.11

 Daytona

-1.11

POSITIVE LOGITS

[];

1.36

 glim

1.26

};

1.18

 disapp

1.15

 diffuse

1.15

 Thief

1.14

 however

1.13

,...

1.12

 though

1.10

 Solitaire

1.10

Activations Density 0.649%

phrases related to public policies and governmental actions

phrases related to assessments and evaluations of standards, particularly in the context of educational or institutional performance

No Comments

No Known Activations