INDEX

Explanations

instances of the word "quite" used in a comparative context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or qualifiers related to understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

olan

-0.87

 DRAG

-0.79

selage

-0.77

lessness

-0.74

uments

-0.71

 bearer

-0.69

elson

-0.65

 Slayer

-0.64

ayer

-0.63

ciplinary

-0.63

POSITIVE LOGITS

spo

0.76

 spoil

0.75

 Enough

0.74

 bothered

0.74

icable

0.73

 enough

0.72

Enough

0.72

fit

0.68

 bother

0.65

 spoon

0.64

Activations Density 0.012%

instances of the word "quite" used in a comparative context

phrases indicating uncertainty or qualifiers related to understanding

No Comments

No Known Activations