INDEX

Explanations

phrases related to proving or demonstrating something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prove" and its variations, indicating assessments or validations of situations or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

arta

-0.85

ataka

-0.75

umbn

-0.75

letal

-0.73

 newsletters

-0.71

adish

-0.69

lished

-0.67

imeters

-0.63

yip

-0.63

ades

-0.63

POSITIVE LOGITS

 incapable

0.86

 invaluable

0.83

 ineffective

0.80

 resilient

0.78

 irresistible

0.74

\\\\\\\\

0.74

 decisive

0.74

stal

0.72

ãĤ¤ãĥĪ

0.72

 victorious

0.70

Activations Density 0.031%

phrases related to proving or demonstrating something

instances of the word "prove" and its variations, indicating assessments or validations of situations or claims

No Comments

No Known Activations