INDEX

Explanations

occurrences of the word "twice" followed by numbers or words

oai_token-act-pair · gpt-3.5-turbo

references to the word "twice" or concepts involving repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

andr

-0.73

rals

-0.68

league

-0.64

endi

-0.63

uctions

-0.63

lements

-0.63

itives

-0.62

uers

-0.62

orts

-0.61

ulner

-0.60

POSITIVE LOGITS

theless

0.84

 consecut

0.82

 apiece

0.72

entimes

0.64

aneously

0.64

fold

0.62

 consecutive

0.62

 yearly

0.62

 dozen

0.61

ieth

0.60

Activations Density 0.019%

occurrences of the word "twice" followed by numbers or words

references to the word "twice" or concepts involving repetition

No Comments

No Known Activations