INDEX

Explanations

terms related to potential opportunities or possibilities

oai_token-act-pair · gpt-3.5-turbo

references to future possibilities or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

breaks

-0.68

tein

-0.64

utenant

-0.62

forcement

-0.61

DCS

-0.60

 Robots

-0.60

ped

-0.60

hement

-0.59

gap

-0.59

wart

-0.58

POSITIVE LOGITS

 prospects

0.94

 prospect

0.91

ively

0.91

uses

0.89

ors

0.85

urally

0.82

us

0.82

urous

0.80

ures

0.79

 futures

0.78

Activations Density 0.040%

terms related to potential opportunities or possibilities

references to future possibilities or potential outcomes

No Comments

No Known Activations