INDEX

Explanations

roles or occupations related to caregiving, management, and professional responsibilities

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.01

2:0.07

3:0.15

4:0.03

5:0.11

6:0.04

7:0.06

8:0.15

9:0.04

10:0.13

11:0.07

Negative Logits

 flakes

-1.00

theless

-0.97

 Everett

-0.97

黒

-0.95

 ceilings

-0.94

 timelines

-0.93

awaru

-0.91

ayne

-0.90

Redd

-0.89

 motions

-0.89

POSITIVE LOGITS

 standpoint

1.12

member

1.08

exclusive

1.07

starter

1.05

statement

1.04

 opener

1.04

 powerhouse

1.00

 contender

1.00

 spokesperson

0.98

 representative

0.97

Activations Density 0.180%

roles or occupations related to caregiving, management, and professional responsibilities

No Comments

No Known Activations