INDEX

Explanations

phrases that seem to be randomly generated or lack coherent meaning

oai_token-act-pair · gpt-3.5-turbo

overall assessments and evaluations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

soDeliveryDate

-0.71

ãĥ©ãĥ³

-0.71

vernment

-0.70

 fortun

-0.64

agara

-0.64

icer

-0.64

trak

-0.60

hots

-0.60

etus

-0.60

vou

-0.59

POSITIVE LOGITS

endif

0.76

 NOTE

0.63

 Walk

0.59

 Delete

0.58

ONSORED

0.57

 SPORTS

0.57

easy

0.56

 Highlights

0.56

<-

0.56

 Also

0.54

Activations Density 0.296%

phrases that seem to be randomly generated or lack coherent meaning

overall assessments and evaluations within the text

No Comments

No Known Activations