INDEX

Explanations

keywords related to bones and bone health

oai_token-act-pair · gpt-3.5-turbo

references to bone health and related medical conditions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eanor

-0.83

olitan

-0.77

atcher

-0.77

arro

-0.75

sers

-0.73

entric

-0.68

HCR

-0.68

PLIED

-0.68

inel

-0.66

committee

-0.66

POSITIVE LOGITS

 marrow

1.60

Bone

1.21

 fide

1.12

bone

1.09

bones

1.08

 bones

1.02

 mineral

0.97

 bone

0.92

headed

0.92

clad

0.92

Activations Density 0.011%

keywords related to bones and bone health

references to bone health and related medical conditions

No Known Activations