INDEX

Explanations

phrases indicating alternative options or choices

oai_token-act-pair · gpt-3.5-turbo

conditional phrases involving the word "or."

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

estro

-0.71

ires

-0.69

tackle

-0.64

"}],"

-0.64

irms

-0.62

IDENT

-0.62

arten

-0.61

igr

-0.60

iesel

-0.60

enses

-0.60

POSITIVE LOGITS

 alternatively

1.29

 rather

1.17

 perhaps

1.05

chard

1.03

 maybe

1.03

 whatever

1.03

 equival

1.02

 indeed

1.01

 worse

0.99

ifice

0.96

Activations Density 0.071%

phrases indicating alternative options or choices

conditional phrases involving the word "or."

No Comments

No Known Activations