INDEX

Explanations

scientific or research-related terms and phrases

oai_token-act-pair · gpt-3.5-turbo

phrases indicating research findings or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Pwr

-0.65

 Trip

-0.64

adelphia

-0.63

 Occupations

-0.62

 Leilan

-0.62

Heb

-0.59

isure

-0.59

imaru

-0.58

 COURT

-0.57

 Purch

-0.57

POSITIVE LOGITS

 methodological

0.76

 widespread

0.73

 empir

0.70

 causation

0.70

 skeptics

0.70

 definitively

0.69

 skepticism

0.65

 scientifically

0.65

 conclusions

0.64

 troubling

0.64

Activations Density 1.082%

scientific or research-related terms and phrases

phrases indicating research findings or conclusions

No Comments

No Known Activations