INDEX

Explanations

instances of locations or events indicated by a specific preposition followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" and its contextually relevant phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vantage

-0.65

ombat

-0.64

dp

-0.60

OWS

-0.58

auer

-0.57

elly

-0.56

achy

-0.55

ensity

-0.55

 âĢķ

-0.55

canon

-0.55

POSITIVE LOGITS

 Zamb

0.66

lication

0.62

uana

0.59

Coh

0.57

Roh

0.56

 shorth

0.53

 recess

0.53

 dusk

0.53

Gim

0.53

 holidays

0.53

Activations Density 0.240%

instances of locations or events indicated by a specific preposition followed by a numerical value

the preposition "in" and its contextually relevant phrases

No Comments

No Known Activations