INDEX

Explanations

phrases indicating beliefs or statements of fact

oai_token-act-pair · gpt-3.5-turbo

phrases expressing skepticism or disbelief

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

vette

-0.70

ouf

-0.67

 arrivals

-0.66

åº

-0.64

WARE

-0.64

ENCY

-0.63

ADVERTISEMENT

-0.60

peria

-0.60

opter

-0.59

ratulations

-0.59

POSITIVE LOGITS

Matrix

0.71

loo

0.68

ById

0.68

alone

0.67

isSpecialOrderable

0.66

ohm

0.65

unes

0.65

washer

0.64

chy

0.63

 raining

0.62

Activations Density 0.440%

phrases indicating beliefs or statements of fact

phrases expressing skepticism or disbelief

No Comments

No Known Activations