INDEX

Explanations

words related to value or worth

oai_token-act-pair · gpt-3.5-turbo

concepts related to value and enjoyment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ept

-0.78

ebus

-0.69

 Aval

-0.68

sup

-0.65

á

-0.64

yer

-0.63

ping

-0.62

chu

-0.62

opathy

-0.61

avis

-0.59

POSITIVE LOGITS

 worthwhile

1.08

terday

1.03

etheless

0.85

 endeavour

0.80

ItemTracker

0.80

allery

0.79

 guiActiveUn

0.79

 traged

0.78

 enjoyable

0.77

 newcom

0.76

Activations Density 0.008%

words related to value or worth

concepts related to value and enjoyment

No Comments

No Known Activations