INDEX

Explanations

phrases related to movement or direction

oai_token-act-pair · gpt-3.5-turbo

phrases indicating direction or movement

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

lux

-0.73

QL

-0.68

 msec

-0.66

Pin

-0.62

Week

-0.61

nih

-0.60

Ŀ

-0.60

rities

-0.59

Ess

-0.59

netflix

-0.57

POSITIVE LOGITS

nings

0.69

anders

0.66

Coy

0.65

 punishing

0.65

undo

0.64

ildo

0.62

 discipl

0.62

inki

0.61

ecast

0.61

ortium

0.60

Activations Density 0.130%

phrases related to movement or direction

phrases indicating direction or movement

No Comments

No Known Activations