INDEX

Explanations

mentions of specific companies or brands

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.04

1:0.13

2:0.02

3:0.03

4:0.02

5:0.38

6:0.02

7:0.01

8:0.03

9:0.10

10:0.13

11:0.03

Negative Logits

 recess

-1.97

 menstru

-1.75

irlf

-1.61

 rite

-1.59

 multiplication

-1.58

 genders

-1.58

 remem

-1.58

blance

-1.58

 flashback

-1.54

 flashbacks

-1.54

POSITIVE LOGITS

 Corporation

2.22

 corporation

2.21

Corp

2.21

 Industries

2.20

 Pharma

2.15

 Corp

2.13

Commerce

2.03

HQ

2.00

�

1.96

Company

1.94

Activations Density 0.180%

mentions of specific companies or brands

No Comments

No Known Activations