INDEX

Explanations

positive sentiments or expressions of appreciation

oai_token-act-pair · gpt-3.5-turbo

positive assessments or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pec

-0.83

onde

-0.69

emic

-0.69

 disadvantage

-0.67

 prematurely

-0.64

 halt

-0.63

idden

-0.63

oubt

-0.62

ueless

-0.62

azard

-0.62

POSITIVE LOGITS

 congr

0.97

Reviewer

0.88

 largeDownload

0.87

 congratulations

0.83

 compliments

0.82

 Especially

0.82

 Artists

0.79

 Congratulations

0.78

 âĿ

0.76

 compliment

0.75

Activations Density 0.930%

positive sentiments or expressions of appreciation

positive assessments or evaluations

No Comments

No Known Activations