INDEX

Explanations

words or prefixes related to minute or small details

oai_token-act-pair · gpt-3.5-turbo

abbreviations and terms related to measurement units or metrics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.89

riott

-0.60

nexus

-0.60

actionDate

-0.60

mony

-0.59

sworth

-0.58

 nature

-0.56

drivers

-0.56

âĸĪâĸĪâĸĪâĸĪ

-0.56

 doors

-0.56

POSITIVE LOGITS

nesota

1.01

amps

0.85

ota

0.82

OTA

0.80

kees

0.73

itol

0.69

igure

0.66

oes

0.66

ippi

0.64

ATURE

0.63

Activations Density 0.065%

words or prefixes related to minute or small details

abbreviations and terms related to measurement units or metrics

No Comments

No Known Activations