INDEX

Explanations

prepositional phrases indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ÂłÂłÂłÂł

-0.70

-0.68

hoe

-0.64

alysed

-0.61

 +---

-0.60

Donnell

-0.60

icter

-0.60

Shell

-0.59

joice

-0.59

Winged

-0.58

POSITIVE LOGITS

 ourselves

0.96

 yourself

0.84

 yourselves

0.84

Ħ¢

0.84

humane

0.84

 oneself

0.84

 somew

0.83

 themselves

0.74

appropriate

0.74

 future

0.74

Activations Density 0.371%

prepositional phrases indicating location or direction

prepositions indicating location or context

No Comments

No Known Activations