INDEX

Explanations

words related to "irrefutable" evidence or conditions

oai_token-act-pair · gpt-3.5-turbo

words related to references and citations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hots

-0.69

 Nanto

-0.67

externalActionCode

-0.62

rers

-0.61

urion

-0.61

artney

-0.60

atche

-0.59

avior

-0.58

 Tycoon

-0.57

apult

-0.56

POSITIVE LOGITS

versible

0.85

ãĥ¼ãĥ

0.77

Bir

0.76

ãĥĥãĤ¯

0.76

borg

0.72

ythm

0.72

ãĥ¼ãĥ«

0.71

isphere

0.69

utable

0.68

und

0.68

Activations Density 0.119%

words related to "irrefutable" evidence or conditions

words related to references and citations

No Comments

No Known Activations