INDEX

Explanations

references to specific company names

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to specific entities or organizations

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

bury

-0.73

edIn

-0.72

tenance

-0.70

stre

-0.69

ications

-0.69

ication

-0.69

 Adin

-0.67

stic

-0.67

 Borough

-0.65

nown

-0.65

POSITIVE LOGITS

adish

0.93

omez

0.90

endered

0.85

reement

0.82

ovie

0.77

APE

0.76

reed

0.76

elman

0.75

apes

0.72

ellen

0.72

Activations Density 0.014%

references to specific company names

abbreviations and acronyms related to specific entities or organizations

No Comments

No Known Activations