INDEX

Explanations

keywords related to specific events or people, such as names, dates, and locations

oai_token-act-pair · gpt-3.5-turbo

significant events or actions related to social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 isEnabled

-0.73

stro

-0.69

ctrl

-0.69

oise

-0.69

brate

-0.68

arge

-0.65

iment

-0.64

lor

-0.63

eworld

-0.63

 Mahjong

-0.62

POSITIVE LOGITS

 Quote

0.77

TED

0.74

ccording

0.72

aneers

0.69

 Experts

0.67

CB

0.65

 Unlike

0.64

 Located

0.61

Unlike

0.60

instead

0.59

Activations Density 0.433%

keywords related to specific events or people, such as names, dates, and locations

significant events or actions related to social interactions

No Comments

No Known Activations