INDEX

Explanations

phrases related to expert recommendations or evaluations

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to recommendations and evaluations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ctor

-0.72

ogg

-0.69

ãĤ¤ãĥĪ

-0.68

cius

-0.68

 Sabb

-0.68

ãĥĩãĤ£

-0.68

KK

-0.67

Ub

-0.66

cler

-0.66

ocy

-0.66

POSITIVE LOGITS

for

0.96

FOR

0.84

for

0.79

 overboard

0.71

 agre

0.70

 lawy

0.70

FOR

0.70

abase

0.70

ioned

0.67

anwhile

0.66

Activations Density 0.169%

phrases related to expert recommendations or evaluations

phrases and terms related to recommendations and evaluations

No Comments

No Known Activations