INDEX

Explanations

phrases indicating strong emotional involvement or significance

oai_token-act-pair · gpt-3.5-turbo

recurring themes related to situations and events

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

assies

-0.70

eworks

-0.63

events

-0.63

seys

-0.62

giene

-0.61

paces

-0.61

ses

-0.59

 Ancients

-0.58

hester

-0.58

 Tanks

-0.58

POSITIVE LOGITS

 unto

0.82

 worthy

0.78

 reminder

0.76

urable

0.76

inel

0.76

less

0.73

 akin

0.71

 oriented

0.71

ually

0.68

 staple

0.68

Activations Density 0.299%

phrases indicating strong emotional involvement or significance

recurring themes related to situations and events

No Comments

No Known Activations