INDEX

Explanations

phrases related to spatial orientation and directions

oai_token-act-pair · gpt-3.5-turbo

specific measurements or conditions related to performance and metrics

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

rig

-0.55

cel

-0.55

Bernie

-0.53

mosp

-0.53

founded

-0.51

 Emmy

-0.51

jen

-0.51

onom

-0.50

CNN

-0.50

jug

-0.48

POSITIVE LOGITS

 cous

0.65

 respectively

0.62

 shenan

0.60

 interchangeable

0.59

 assum

0.59

yip

0.58

 alternating

0.58

 increments

0.57

 indu

0.56

 thereby

0.55

Activations Density 1.340%

phrases related to spatial orientation and directions

specific measurements or conditions related to performance and metrics

No Comments

No Known Activations