INDEX

Explanations

phrases indicating a comparison between different aspects or options

oai_token-act-pair · gpt-3.5-turbo

phrases that include alternatives or comparisons

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

successfully

-0.78

igned

-0.68

ially

-0.64

ETS

-0.64

umerous

-0.63

requently

-0.62

Duration

-0.62

egu

-0.60

ottesville

-0.59

erest

-0.59

POSITIVE LOGITS

whatever

1.74

 whatever

1.73

 something

1.42

acle

1.36

 anything

1.28

 whoever

1.27

 somet

1.23

 whichever

1.20

chard

1.20

 wherever

1.13

Activations Density 0.156%

phrases indicating a comparison between different aspects or options

phrases that include alternatives or comparisons

No Comments

No Known Activations