INDEX

Explanations

mentions of the word "water"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "ater" likely indicating references to water or related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Disk

-0.68

ured

-0.67

ures

-0.66

 diabetic

-0.64

 Chao

-0.62

INS

-0.62

 fung

-0.61

 sanity

-0.60

Ko

-0.60

 Pigs

-0.60

POSITIVE LOGITS

pillar

1.09

IAL

0.97

ater

0.93

apy

0.93

ickson

0.90

idon

0.88

eor

0.86

iatus

0.85

apter

0.84

ites

0.84

Activations Density 0.018%

mentions of the word "water"

mentions of the word "ater" likely indicating references to water or related topics

No Comments

No Known Activations