INDEX

Explanations

phrases related to actions or processes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the return or presence of items or entities

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

ONSORED

-0.90

OB

-0.78

\\\\\\\\

-0.73

é¾įåĸļå£«

-0.71

jandro

-0.67

isSpecialOrderable

-0.66

issance

-0.65

URRENT

-0.65

éĹ

-0.65

ARY

-0.65

POSITIVE LOGITS

 prolifer

0.94

 abound

0.93

 necks

0.89

 nests

0.83

 everywhere

0.82

poons

0.82

uits

0.75

 Held

0.72

 plentiful

0.71

 explode

0.70

Activations Density 0.908%

phrases related to actions or processes

phrases indicating the return or presence of items or entities

No Comments

No Known Activations