INDEX

Explanations

prepositions followed by a number

oai_token-act-pair · gpt-3.5-turbo

prepositions and related phrases indicating direction or purpose

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

Newsletter

-0.70

eno

-0.59

Hot

-0.59

Residents

-0.58

hots

-0.58

Ľ

-0.57

itiz

-0.57

Definition

-0.57

Blue

-0.57

 Affordable

-0.56

POSITIVE LOGITS

 whom

0.75

ardless

0.70

arently

0.66

 which

0.65

 unsus

0.64

 apologies

0.62

 perhaps

0.62

 preferably

0.62

cause

0.62

elling

0.61

Activations Density 0.394%

prepositions followed by a number

prepositions and related phrases indicating direction or purpose

No Comments

No Known Activations