INDEX

Explanations

references to a particular section or gallery in an article or story

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a return to a previous topic or idea

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

igham

-0.69

merce

-0.68

phas

-0.67

lication

-0.67

icipated

-0.64

ometimes

-0.63

 conveyed

-0.61

Ö¼

-0.60

endi

-0.60

phalt

-0.60

POSITIVE LOGITS

wing

0.74

 Main

0.68

 haunt

0.67

 grid

0.66

forth

0.62

ggles

0.61

 Hick

0.61

 Races

0.61

 shore

0.60

ven

0.60

Activations Density 0.034%

references to a particular section or gallery in an article or story

phrases indicating a return to a previous topic or idea

No Comments

No Known Activations