INDEX

Explanations

words related to a specific name or term 'Sid'

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Sid" and its variations 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

anwhile

-0.78

ITNESS

-0.74

ãģ£

-0.74

awaru

-0.72

amins

-0.70

è¦ļéĨĴ

-0.70

asca

-0.68

andise

-0.68

çĦ

-0.65

AIN

-0.65

POSITIVE LOGITS

eways

1.21

 Meier

1.04

etr

1.02

Sid

0.96

eless

0.81

eway

0.80

 Mubarak

0.78

emy

0.75

escription

0.73

eworks

0.73

Activations Density 0.008%

words related to a specific name or term 'Sid'

mentions of the name "Sid" and its variations in various contexts

No Comments

No Known Activations