INDEX

Explanations

mentions of body parts and medical terms related to injuries

oai_token-act-pair · gpt-3.5-turbo

phrases related to emotional or moral judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entimes

-0.53

ãĥĥãĥī

-0.45

bably

-0.44

 firsthand

-0.44

pmwiki

-0.43

ufficient

-0.42

ONSORED

-0.42

erous

-0.41

phasis

-0.41

arily

-0.40

POSITIVE LOGITS

 organise

0.64

 analyse

0.58

 organised

0.55

 analysed

0.55

 realise

0.54

 Gaddafi

0.53

NHS

0.53

 Fifa

0.52

 Nato

0.52

 enqu

0.50

Activations Density 3.168%

mentions of body parts and medical terms related to injuries

phrases related to emotional or moral judgments

No Comments

No Known Activations