INDEX

Explanations

terms related to familial relationships and social roles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.11

1:0.14

2:0.05

3:0.09

4:0.04

5:0.18

6:0.02

7:0.02

8:0.17

9:0.06

10:0.04

11:0.03

Negative Logits

="#

-1.42

 suspected

-1.40

 recalling

-1.38

dropping

-1.36

lig

-1.36

inous

-1.30

 alleged

-1.29

 claimed

-1.27

hetical

-1.25

 disputed

-1.25

POSITIVE LOGITS

 …"

2.08

 Indra

1.90

etc

1.81

…

1.75

….

1.64

,,,,

1.61

sic

1.60

..."

1.58

…

1.57

…"

1.55

Activations Density 0.027%

terms related to familial relationships and social roles

No Comments

No Known Activations