INDEX

Explanations

phrases indicating a transition to a new topic or idea

oai_token-act-pair · gpt-3.5-turbo

references to progression or transitions in ideas or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

she

-0.70

ricular

-0.65

quer

-0.63

anas

-0.58

gad

-0.57

stru

-0.57

sylv

-0.56

ryn

-0.56

 vict

-0.56

orld

-0.54

POSITIVE LOGITS

 nicely

0.90

us

0.80

me

0.77

why

0.76

 neatly

0.75

 Canaver

0.75

 begs

0.75

inently

0.74

 Patreon

0.68

 Birch

0.67

Activations Density 0.238%

phrases indicating a transition to a new topic or idea

references to progression or transitions in ideas or topics

No Comments

No Known Activations