INDEX

Explanations

phrases related to justification or reasoning

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "basis" or foundational reasoning for claims or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

icer

-0.79

ascus

-0.71

quer

-0.71

 Patriarch

-0.70

edo

-0.67

resent

-0.65

apes

-0.64

chrom

-0.63

jri

-0.63

Town

-0.62

POSITIVE LOGITS

 basis

0.89

 grounds

0.85

 Grounds

0.78

tenance

0.75

grounds

0.73

 premise

0.70

fy

0.70

tyard

0.68

 Formula

0.67

endment

0.66

Activations Density 0.045%

phrases related to justification or reasoning

references to the concept of "basis" or foundational reasoning for claims or arguments

No Comments

No Known Activations