INDEX

Explanations

prepositions and conjunctions in meaningful phrases

oai_token-act-pair · gpt-3.5-turbo

patterns of connections and relationships in sentences

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

versions

-0.75

æ©Ł

-0.64

elman

-0.63

Ļ½

-0.62

pires

-0.61

 nonetheless

-0.61

isine

-0.60

 Bever

-0.60

pin

-0.59

©¶æ¥µ

-0.59

POSITIVE LOGITS

tein

0.69

ukemia

0.68

ionage

0.64

itatively

0.64

 defiance

0.63

geries

0.63

lihood

0.62

 guiActiveUn

0.61

qt

0.60

achine

0.60

Activations Density 0.204%

prepositions and conjunctions in meaningful phrases

patterns of connections and relationships in sentences

No Comments

No Known Activations