INDEX

Explanations

references to geographical locations, specifically ports

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "port" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cumbers

-0.70

 blinking

-0.68

 whiff

-0.62

 smokes

-0.61

awks

-0.60

 resil

-0.59

 heck

-0.57

aida

-0.57

 identifying

-0.56

awk

-0.55

POSITIVE LOGITS

folios

1.39

port

1.27

folio

1.25

rait

1.18

raits

1.08

ugal

0.99

eering

0.91

PORT

0.90

portion

0.84

ilage

0.84

Activations Density 0.006%

references to geographical locations, specifically ports

mentions of the word "port" in various contexts

No Comments

No Known Activations