INDEX

Explanations

references to legal and judicial issues

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

0:0.05

1:0.06

2:0.02

3:0.03

4:0.02

5:0.44

6:0.02

7:0.01

8:0.05

9:0.10

10:0.11

11:0.05

Negative Logits

Americ

-1.74

antam

-1.66

olars

-1.64

picture

-1.63

Reader

-1.60

Buzz

-1.57

AMY

-1.57

Scroll

-1.56

Types

-1.54

��

-1.53

POSITIVE LOGITS

 neglig

2.12

 negligence

2.07

 mishand

2.03

 misrepresent

2.00

 botched

1.95

 breached

1.91

 refusal

1.91

 misuse

1.91

 misled

1.88

 dispar

1.88

Activations Density 0.664%

references to legal and judicial issues

No Comments

No Known Activations