INDEX

Explanations

verbs related to actions taken in response to a situation

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

0:0.08

1:0.03

2:0.22

3:0.08

4:0.02

5:0.09

6:0.04

7:0.05

8:0.09

9:0.07

10:0.12

11:0.05

Negative Logits

mare

-1.13

nin

-1.09

 bumps

-1.08

aceae

-1.06

 gonna

-1.01

nikov

-0.97

 gotta

-0.97

pmwiki

-0.95

assic

-0.95

nings

-0.95

POSITIVE LOGITS

igate

1.20

uate

1.14

SPONSORED

1.05

ilaterally

1.02

existent

0.98

 disposal

0.97

venge

0.96

Channel

0.94

arget

0.94

 fullest

0.93

Activations Density 0.286%

verbs related to actions taken in response to a situation

No Comments

No Known Activations