INDEX

Explanations

phrases related to medical trials and experiments

oai_token-act-pair · gpt-3.5-turbo

references to clinical trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

flush

-0.79

York

-0.71

afort

-0.69

BN

-0.68

iak

-0.65

leted

-0.65

si

-0.64

aths

-0.64

address

-0.64

Solid

-0.63

POSITIVE LOGITS

 Trials

1.23

 trials

1.18

 trial

0.93

 Trial

0.90

 "$:/

0.85

avorite

0.85

hower

0.75

 testing

0.75

poon

0.71

nesday

0.71

Activations Density 0.010%

phrases related to medical trials and experiments

references to clinical trials

No Comments

No Known Activations