INDEX

Explanations

terms related to different areas or topics of interest

oai_token-act-pair · gpt-3.5-turbo

references to specific areas or topics of discussion

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

itous

-0.73

enstein

-0.72

arus

-0.70

lio

-0.69

guided

-0.68

essed

-0.67

inn

-0.67

esses

-0.66

icious

-0.66

pter

-0.66

POSITIVE LOGITS

 areas

0.92

 area

0.87

manship

0.81

 Areas

0.77

 proble

0.76

icals

0.70

folios

0.67

 expertise

0.66

icular

0.66

 specialization

0.66

Activations Density 0.034%

terms related to different areas or topics of interest

references to specific areas or topics of discussion

No Comments

No Known Activations