INDEX

Explanations

references to reports, stories, documents, and petitions

oai_token-act-pair · gpt-3.5-turbo

formal documents and reports related to various topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tics

-0.80

ernels

-0.80

ses

-0.79

 Cups

-0.77

 Empires

-0.73

 Instant

-0.73

brids

-0.72

 Machines

-0.72

 Occupations

-0.72

ospels

-0.70

POSITIVE LOGITS

 called

0.81

 titled

0.80

dylib

0.70

 headlined

0.70

 dubbed

0.69

 Called

0.69

 consisting

0.68

 reminiscent

0.67

ogram

0.67

 resembling

0.66

Activations Density 0.409%

references to reports, stories, documents, and petitions

formal documents and reports related to various topics

No Comments

No Known Activations