INDEX

Explanations

words related to prefixes in the context of linguistics

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

0:0.05

1:0.04

2:0.18

3:0.05

4:0.10

5:0.06

6:0.04

7:0.04

8:0.08

9:0.21

10:0.07

11:0.03

Negative Logits

��

-1.55

schild

-1.48

ipeg

-1.47

odcast

-1.39

onge

-1.31

atonin

-1.26

akeru

-1.25

wagen

-1.25

sbm

-1.24

okia

-1.24

POSITIVE LOGITS

 suffix

1.76

 curses

1.44

 curse

1.42

 charm

1.39

 modifiers

1.33

 describing

1.32

 invoked

1.22

 descriptor

1.22

 charms

1.21

 specifying

1.20

Activations Density 0.003%

words related to prefixes in the context of linguistics

No Comments

No Known Activations