INDEX

Explanations

phrases related to possibility or feasibility

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate possibility or likelihood

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

 pulp

-0.72

endon

-0.69

anian

-0.63

 menace

-0.60

hoe

-0.57

haw

-0.55

 transcript

-0.55

agos

-0.55

 mouths

-0.54

igl

-0.54

POSITIVE LOGITS

uti

0.70

aceae

0.62

zza

0.60

OVA

0.60

 justifies

0.58

undai

0.57

0.56

answered

0.55

oso

0.54

osi

0.52

Activations Density 0.813%

phrases related to possibility or feasibility

phrases that indicate possibility or likelihood

No Comments

No Known Activations