INDEX

Explanations

references to quantity and abundance in a context related to capabilities and attributes

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

0:0.15

1:0.07

2:0.17

3:0.04

4:0.05

5:0.06

6:0.02

7:0.03

8:0.18

9:0.05

10:0.04

11:0.08

Negative Logits

stuff

-2.06

levant

-1.91

*/(

-1.88

selves

-1.86

oples

-1.68

illac

-1.66

 anyways

-1.63

 respectively

-1.57

sters

-1.57

 Stuff

-1.56

POSITIVE LOGITS

 understatement

2.11

 avoidance

1.96

 blindness

1.90

 indifference

1.80

 absence

1.79

 reluctance

1.78

 amplification

1.75

 resemblance

1.75

ハ

1.74

 rejection

1.69

Activations Density 0.008%

references to quantity and abundance in a context related to capabilities and attributes

No Comments

No Known Activations