INDEX

Explanations

words related to trekking or hiking

oai_token-act-pair · gpt-3.5-turbo

references to trekking or journeying activities

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

death

-0.75

confidence

-0.70

ancies

-0.70

uracy

-0.70

encies

-0.69

 tense

-0.65

 IMAGES

-0.64

recy

-0.63

ENCY

-0.62

urity

-0.62

POSITIVE LOGITS

 trek

1.31

kers

1.06

king

1.03

kies

0.98

 hiking

0.91

 Everest

0.81

edIn

0.80

 Expedition

0.79

itudinal

0.77

ker

0.75

Activations Density 0.007%

words related to trekking or hiking

references to trekking or journeying activities

No Comments

No Known Activations