INDEX

Explanations

words related to physical or medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to conditions or states, particularly in medical or situational 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

enic

-0.73

sonian

-0.73

rious

-0.73

ramid

-0.73

azi

-0.66

ron

-0.63

yright

-0.63

ashington

-0.63

ritz

-0.62

endar

-0.62

POSITIVE LOGITS

ality

1.04

quo

0.90

 worsened

0.89

 deterior

0.87

ally

0.87

 deteriorated

0.83

aldehyde

0.82

 wors

0.78

eq

0.76

ements

0.75

Activations Density 0.033%

words related to physical or medical conditions

terms related to conditions or states, particularly in medical or situational contexts

No Comments

No Known Activations