INDEX

Explanations

indications of a reduction or decrease in value or amount

oai_token-act-pair · gpt-3.5-turbo

the phrase "Less than" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĹ¼

-0.76

TAG

-0.65

ãĤ±

-0.63

DK

-0.62

 supremacy

-0.61

 Reconstruction

-0.60

Draft

-0.59

mberg

-0.58

 Origins

-0.57

TRY

-0.57

POSITIVE LOGITS

ened

1.00

 than

0.88

ening

0.84

reet

0.81

ensive

0.81

thumbnails

0.80

ons

0.80

erton

0.79

cipl

0.75

onest

0.74

Activations Density 0.039%

indications of a reduction or decrease in value or amount

the phrase "Less than" in various contexts

No Comments

No Known Activations