INDEX

Explanations

verbs or noun phrases related to desires or intentions

oai_token-act-pair · gpt-3.5-turbo

phrases expressing collective opinions or feelings

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

OGR

-0.70

ounded

-0.69

berus

-0.67

 Providence

-0.64

inventoryQuantity

-0.64

ullivan

-0.63

urrection

-0.62

rontal

-0.61

iliate

-0.61

adem

-0.60

POSITIVE LOGITS

 alike

0.84

 except

0.84

else

0.69

 Perspective

0.69

 Dame

0.66

jac

0.66

 knows

0.66

perty

0.64

lishes

0.63

kn

0.62

Activations Density 0.211%

verbs or noun phrases related to desires or intentions

phrases expressing collective opinions or feelings

No Comments

No Known Activations