INDEX

Explanations

words related to acronyms and abbreviations

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nesday

-0.67

 grit

-0.64

 Cheong

-0.60

 independents

-0.60

gaard

-0.59

anchester

-0.59

 Piet

-0.58

 Yanuk

-0.58

 Pence

-0.57

 Gret

-0.57

POSITIVE LOGITS

ioxide

0.79

emn

0.77

Weather

0.75

pillar

0.74

ophen

0.74

eta

0.74

ola

0.71

emia

0.70

lia

0.70

ulum

0.70

Activations Density 0.143%

words related to acronyms and abbreviations

abbreviations or acronyms

No Comments

No Known Activations