INDEX

Explanations

the word 'experience'

oai_token-act-pair · gpt-3.5-turbo

words related to experiences or experiments

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

 Appalachian

-0.72

 Leilan

-0.72

uyomi

-0.67

brush

-0.67

 vigil

-0.66

 Skydragon

-0.66

 Tate

-0.63

 Saber

-0.62

 Appalach

-0.61

 action

-0.60

POSITIVE LOGITS

ienced

1.61

iments

1.40

iences

1.39

iment

1.38

ience

1.28

imental

1.28

ient

1.18

ien

1.03

icion

0.98

ients

0.94

Activations Density 0.015%

the word 'experience'

words related to experiences or experiments

No Comments

No Known Activations