INDEX

Explanations

words related to locations or places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ap"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

BuyableInstoreAndOnline

-0.76

 Masquerade

-0.69

 phyl

-0.69

 Carib

-0.67

 cigars

-0.66

 Corsair

-0.65

 Rove

-0.64

milo

-0.64

âĸ¬âĸ¬

-0.63

knit

-0.63

POSITIVE LOGITS

olitan

1.21

alm

1.21

oleon

1.19

onent

1.16

apa

1.13

ower

1.13

oton

1.13

ocalypse

1.12

otrop

1.10

ocalyptic

1.09

Activations Density 0.015%

words related to locations or places

occurrences of the substring "ap"

No Comments

No Known Activations