INDEX

Explanations

numerical values within a specific range

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

ument

-0.76

luence

-0.70

alach

-0.67

cill

-0.67

acre

-0.67

MpServer

-0.66

intend

-0.64

ropri

-0.63

enium

-0.62

oc

-0.61

POSITIVE LOGITS

 Pharaoh

0.72

 Lumpur

0.63

 darts

0.62

 Languages

0.61

 Jakarta

0.60

 stairs

0.60

aq

0.59

terms

0.57

 shoots

0.57

 Kuala

0.57

Activations Density 0.062%

numerical values within a specific range

numerical data and statistics

No Comments

No Known Activations