INDEX

Explanations

phrases related to acceptance and responsibility

oai_token-act-pair · gpt-3.5-turbo 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.02

2:0.14

3:0.05

4:0.31

5:0.05

6:0.02

7:0.02

8:0.14

9:0.10

10:0.04

11:0.02

Negative Logits

abouts

-1.91

itol

-1.54

lycer

-1.47

acca

-1.47

ansk

-1.43

ibaba

-1.40

imes

-1.39

ı

-1.38

isher

-1.35

heng

-1.34

POSITIVE LOGITS

 unres

1.65

 consensual

1.51

 membership

1.51

 polygamy

1.46

 Accept

1.44

 homosexuality

1.42

 paternity

1.42

 pronouns

1.36

 fortun

1.36

 disbel

1.35

Activations Density 0.007%

phrases related to acceptance and responsibility

No Comments

No Known Activations