INDEX

Explanations

terms related to connections, relationships, and interactions

oai_token-act-pair · gpt-3.5-turbo

connections and relationships within various contexts

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

Cola

-0.65

ocument

-0.62

ĳå£«

-0.61

hovah

-0.59

owe

-0.58

angelo

-0.56

bilt

-0.56

pection

-0.56

ãĤ¢ãĥ«

-0.55

ãĤ®

-0.55

POSITIVE LOGITS

 Dialogue

0.64

apters

0.57

origin

0.52

tones

0.52

ioxide

0.52

ourses

0.51

isively

0.51

channelAvailability

0.50

 intens

0.49

 between

0.49

Activations Density 1.264%

terms related to connections, relationships, and interactions

connections and relationships within various contexts

No Comments

No Known Activations