INDEX

Explanations

textual delimiters or separators

oai_token-act-pair · gpt-3.5-turbo

punctuation and formatting elements in the text

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

heit

-0.75

 Reincarnated

-0.67

apon

-0.62

cius

-0.61

mbuds

-0.61

icent

-0.61

boro

-0.61

say

-0.61

inyl

-0.60

ars

-0.60

POSITIVE LOGITS

ÂłÂłÂłÂłÂłÂłÂłÂł

0.66

ÂłÂłÂł

0.63

ÂłÂłÂłÂł

0.62

ONSORED

0.61

ä½¿

0.60

 landfall

0.60

 compr

0.59

eways

0.59

ãĤ¨ãĥ«

0.58

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.58

Activations Density 0.219%

textual delimiters or separators

punctuation and formatting elements in the text

No Comments

No Known Activations