INDEX

Explanations

medical terms related to mental cognitive function

oai_token-act-pair · gpt-3.5-turbo

terms related to inaccuracies and medical conditions in a context that suggests implications for their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

lad

-0.72

 looms

-0.71

ount

-0.64

ographs

-0.63

icular

-0.63

 Brisbane

-0.63

hend

-0.63

 stew

-0.62

itionally

-0.62

 Waterloo

-0.62

POSITIVE LOGITS

 Accuracy

2.97

uracy

2.20

 Availability

1.12

nesia

1.04

iability

1.00

 Ability

0.80

Atk

0.78

 Jarrett

0.76

ateurs

0.74

Abs

0.73

Activations Density 0.021%

medical terms related to mental cognitive function

terms related to inaccuracies and medical conditions in a context that suggests implications for their significance

No Comments

No Known Activations