INDEX

Explanations

terms related to predictions and forecasting

oai_token-act-pair · gpt-3.5-turbo

phrases related to healthcare and predictive analytics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

krit

-0.77

Dub

-0.73

©¶æ¥µ

-0.72

¶ħ

-0.71

ĸļ

-0.65

 Goddard

-0.63

minus

-0.63

 hindsight

-0.62

âĢ¦âĢ¦âĢ¦âĢ¦

-0.62

 analogy

-0.62

POSITIVE LOGITS

 optimal

0.93

 optimum

0.82

 strengths

0.79

 vulnerabilities

0.76

 weaknesses

0.74

 fitt

0.73

 appropriate

0.72

 likely

0.70

 vulner

0.70

 safely

0.70

Activations Density 0.348%

terms related to predictions and forecasting

phrases related to healthcare and predictive analytics in various contexts

No Comments

No Known Activations