INDEX

Explanations

words related to qualities or characteristics

oai_token-act-pair · gpt-3.5-turbo

descriptions of quality or performance indicators

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

ãģĻ

-0.58

 urgently

-0.57

 shalt

-0.56

Hes

-0.55

 instead

-0.55

=#

-0.54

ãģĹ

-0.54

 Instruct

-0.53

ãĤĬ

-0.53

 flashed

-0.51

POSITIVE LOGITS

due

0.64

yet

0.64

due

0.63

jri

0.62

antry

0.62

Reviewer

0.60

 lately

0.58

luster

0.57

:(

0.55

bledon

0.55

Activations Density 1.199%

words related to qualities or characteristics

descriptions of quality or performance indicators

No Comments

No Known Activations