INDEX

Explanations

discussions related to politics and technology

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

0:0.08

1:0.03

2:0.11

3:0.15

4:0.05

5:0.08

6:0.04

7:0.02

8:0.16

9:0.13

10:0.08

11:0.02

Negative Logits

stood

-1.21

claimed

-1.14

angan

-1.11

cess

-1.08

 rece

-1.06

exempt

-1.05

rendered

-1.04

 ponds

-1.04

 loose

-1.02

 Dwell

-1.01

POSITIVE LOGITS

 proverb

1.25

OPLE

1.21

 amen

1.15

 Siri

1.14

��

1.13

soType

1.10

 Bezos

1.10

ptroller

1.07

 theorem

1.07

 newsp

1.07

Activations Density 0.010%

discussions related to politics and technology

No Comments

No Known Activations