INDEX

Explanations

references to specific locations or contexts related to discoveries

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

0:0.02

1:0.01

2:0.09

3:0.08

4:0.14

5:0.02

6:0.03

7:0.27

8:0.04

9:0.03

10:0.12

11:0.08

Negative Logits

verages

-1.82

 adject

-1.61

ctions

-1.58

isSpecialOrderable

-1.44

pport

-1.44

enance

-1.43

idity

-1.41

ctive

-1.40

 patience

-1.36

 opin

-1.35

POSITIVE LOGITS

 Mystery

1.51

 sparking

1.48

 Mysteries

1.45

Pick

1.45

ource

1.41

 Aerial

1.24

 Steal

1.24

 uncover

1.24

 illegally

1.22

 unknown

1.22

Activations Density 0.006%

references to specific locations or contexts related to discoveries

No Comments

No Known Activations