INDEX

Explanations

phrases related to proving oneself or oneself's abilities

oai_token-act-pair · gpt-3.5-turbo

references to individuals proving themselves or their capabilities

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

 IMAGES

-0.74

anon

-0.69

catentry

-0.69

letal

-0.68

 newsletters

-0.64

 shares

-0.64

enhagen

-0.64

NCT

-0.63

inately

-0.63

rica

-0.62

POSITIVE LOGITS

worthiness

0.83

Applic

0.79

 Guilty

0.77

IER

0.74

 useful

0.71

Fail

0.69

Notable

0.68

 worthy

0.68

 Canad

0.67

 invaluable

0.67

Activations Density 0.087%

phrases related to proving oneself or oneself's abilities

references to individuals proving themselves or their capabilities

No Comments

No Known Activations