INDEX

Explanations

past or present participles indicative of a state of being or action

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

past tense verbs and phrases indicating actions or states of being

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.01

1:0.10

2:0.10

3:0.05

4:0.01

5:0.06

6:0.11

7:0.11

8:0.09

9:0.08

10:0.13

11:0.08

Negative Logits

 hindsight

-1.12

 Plague

-1.03

 Flake

-0.99

 contrary

-0.96

 Panic

-0.95

 Freak

-0.94

uit

-0.92

Pep

-0.91

 Sever

-0.90

 Hacker

-0.89

POSITIVE LOGITS

rongh

1.37

orthy

1.16

Associated

1.16

ibli

1.07

ucl

1.05

artment

1.04

�

1.03

udeau

1.02

cling

1.02

zl

1.01

Activations Density 0.114%

past or present participles indicative of a state of being or action

past tense verbs and phrases indicating actions or states of being

No Known Activations

past or present participles indicative of a state of being or action

past tense verbs and phrases indicating actions or states of being

No Known Activations