INDEX

Explanations

words related to scientific theories and hypotheses

oai_token-act-pair · gpt-3.5-turbo

concepts related to scientific inquiry and hypotheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.85

çīĪ

-0.79

©¶æ¥µ

-0.78

senal

-0.72

BuyableInstoreAndOnline

-0.71

cussion

-0.69

audi

-0.67

 Werewolf

-0.64

Camp

-0.63

Shield

-0.63

POSITIVE LOGITS

 abstract

0.86

 oneself

0.80

 determin

0.76

 intellig

0.75

 uncond

0.74

 stimulus

0.74

 imperfect

0.73

 finite

0.73

 intrinsically

0.72

 necessarily

0.72

Activations Density 1.345%

words related to scientific theories and hypotheses

concepts related to scientific inquiry and hypotheses

No Comments

No Known Activations