INDEX

Explanations

phrases related to objects or places that are adorned or decorated

oai_token-act-pair · gpt-3.5-turbo

terms related to decoration and embellishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

RS

-0.73

demand

-0.70

FS

-0.67

PU

-0.65

$$$$

-0.65

lev

-0.64

LS

-0.64

ffic

-0.62

ent

-0.60

akes

-0.60

POSITIVE LOGITS

 decorated

0.98

nesday

0.83

 decorations

0.82

ocument

0.78

 decoration

0.78

 Ribbon

0.73

oshenko

0.71

ModLoader

0.70

teness

0.70

 crates

0.70

Activations Density 0.021%

phrases related to objects or places that are adorned or decorated

terms related to decoration and embellishment

No Comments

No Known Activations