INDEX

Explanations

asymmetrical and symmetrical patterns, shapes, or distributions

oai_token-act-pair · gpt-3.5-turbo

terms related to asymmetry and symmetry 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Footnote

-0.89

 Muse

-0.77

 Dough

-0.71

 Spur

-0.71

Interstitial

-0.71

 Loans

-0.70

Page

-0.69

 Advertisement

-0.69

Assembly

-0.68

 Campbell

-0.67

POSITIVE LOGITS

etrical

1.56

etric

1.49

 asymm

1.30

 symm

1.25

etry

1.24

etr

1.19

ymm

1.14

 symmetry

1.06

yip

1.00

ropy

0.99

Activations Density 0.014%

asymmetrical and symmetrical patterns, shapes, or distributions

terms related to asymmetry and symmetry in various contexts

No Comments

No Known Activations