INDEX

Explanations

keywords related to programming in the C language

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.04

2:0.07

3:0.07

4:0.07

5:0.07

6:0.07

7:0.09

8:0.14

9:0.12

10:0.08

11:0.04

Negative Logits

Benz

-1.48

 inhal

-1.24

Heart

-1.20

dule

-1.16

 Reincarn

-1.13

 Diesel

-1.11

externalActionCode

-1.10

 MDMA

-1.08

iso

-1.08

LSD

-1.07

POSITIVE LOGITS

pat

1.21

 counsel

1.15

ople

1.12

ilers

1.11

ollen

1.09

 courtroom

1.09

>:

1.07

]:

1.05

arton

1.03

 surn

1.02

Activations Density 0.002%

keywords related to programming in the C language

No Comments

No Known Activations