INDEX

Explanations

prepositions followed by a noun phrase which often involves various forms of entities such as chemicals, locations, and individuals

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating relationships or connections

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

sers

-0.68

qv

-0.64

 ãĤµ

-0.63

irez

-0.62

wo

-0.62

ten

-0.61

SPA

-0.59

,[

-0.59

js

-0.58

 Citiz

-0.58

POSITIVE LOGITS

Tel

0.70

uyomi

0.70

 Gamble

0.68

affer

0.66

 contrad

0.64

 Jane

0.59

ĸļ

0.59

Î³

0.58

 Baal

0.58

isine

0.57

Activations Density 0.434%

prepositions followed by a noun phrase which often involves various forms of entities such as chemicals, locations, and individuals

prepositions indicating relationships or connections

No Comments

No Known Activations