INDEX

Explanations

parents or parental figures expressed in various contexts and perspectives

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouls

-0.72

aus

-0.65

 âĵĺ

-0.64

onies

-0.63

bably

-0.61

ogue

-0.60

umo

-0.60

pages

-0.60

oÄŁ

-0.59

oshenko

-0.59

POSITIVE LOGITS

 myself

0.97

 ourselves

0.80

 educator

0.77

itect

0.76

 historian

0.70

ForgeModLoader

0.70

 reviewer

0.69

 adop

0.68

 witness

0.66

 empath

0.64

Activations Density 0.154%

parents or parental figures expressed in various contexts and perspectives

No Comments

No Known Activations