INDEX

Explanations

phrases related to returning or going back to a particular place or role

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a return to a specific location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

merce

-0.76

 conveyed

-0.66

SourceFile

-0.65

ihad

-0.64

 gone

-0.64

holes

-0.61

VPN

-0.61

Mah

-0.60

erity

-0.60

 precursor

-0.59

POSITIVE LOGITS

 haunt

1.16

 shore

0.92

 grips

0.79

 fold

0.78

 pasture

0.78

 shores

0.78

 prominence

0.75

 fray

0.75

 earth

0.74

 Earth

0.71

Activations Density 0.058%

phrases related to returning or going back to a particular place or role

phrases indicating a return to a specific location or context

No Comments

No Known Activations