INDEX

Explanations

details or specific aspects in a text

oai_token-act-pair · gpt-3.5-turbo

references to memories, lessons learned, and various concepts associated with life experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Staten

-0.63

noon

-0.61

ATIONAL

-0.60

 Bulldogs

-0.60

 millenn

-0.59

Synopsis

-0.58

ILE

-0.57

esters

-0.57

iatus

-0.56

onel

-0.56

POSITIVE LOGITS

mith

1.11

peed

1.07

hare

1.05

matter

1.04

 thereof

1.03

etting

1.01

pring

1.00

poon

1.00

omething

1.00

ilver

1.00

Activations Density 0.482%

details or specific aspects in a text

references to memories, lessons learned, and various concepts associated with life experiences

No Comments

No Known Activations