INDEX

Explanations

terms related to legal investigations and evidence analysis

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

references to investigative analysis and examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

1:0.04

2:0.09

3:0.09

4:0.05

5:0.08

6:0.03

7:0.03

8:0.26

9:0.10

10:0.07

11:0.03

Negative Logits

の�

-1.19

 Slam

-1.16

owners

-1.09

 Crew

-1.06

Cly

-1.04

Magikarp

-1.02

Club

-1.01

�

-1.01

Syl

-0.99

WER

-0.99

POSITIVE LOGITS

 favorably

1.44

 facets

1.43

 totality

1.31

 objectively

1.25

 unfold

1.25

 patterns

1.23

 morphology

1.22

 pertinent

1.21

 stimuli

1.21

effic

1.20

Activations Density 0.043%

terms related to legal investigations and evidence analysis

references to investigative analysis and examinations

No Comments

No Known Activations