INDEX

Explanations

terms related to neurology and psychological fields

oai_token-act-pair · gpt-3.5-turbo

terms related to neurobiology and psychology

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

Kem

-0.68

raped

-0.65

 allowances

-0.63

MAC

-0.62

 kicker

-0.60

AAF

-0.59

cember

-0.58

 compr

-0.58

 torches

-0.58

wit

-0.57

POSITIVE LOGITS

rencies

0.83

SpaceEngineers

0.78

¬

0.73

nia

0.73

idon

0.70

ioxide

0.69

uct

0.68

ific

0.68

rules

0.67

osate

0.67

Activations Density 0.133%

terms related to neurology and psychological fields

terms related to neurobiology and psychology

No Comments

No Known Activations