INDEX

Explanations

locations or positions within a sentence

oai_token-act-pair · gpt-3.5-turbo

prepositions and related phrases indicating temporal or locational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

/-

-0.84

 reciproc

-0.58

agog

-0.57

 laure

-0.57

OPA

-0.57

ega

-0.56

 groove

-0.55

vit

-0.55

ful

-0.55

 polymorph

-0.55

POSITIVE LOGITS

Ott

0.70

terms

0.67

 Cosponsors

0.67

okingly

0.64

ãĥĥãĥī

0.64

 Barcl

0.63

WT

0.62

dn

0.60

ooked

0.59

zhen

0.59

Activations Density 0.716%

locations or positions within a sentence

prepositions and related phrases indicating temporal or locational context

No Comments

No Known Activations