INDEX

Explanations

terms related to medical conditions and anatomy, focusing on words ending in "ary"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "ary"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ierrez

-0.72

ests

-0.72

ided

-0.67

essee

-0.66

ossibility

-0.66

imately

-0.65

oba

-0.65

ible

-0.64

ergy

-0.64

ERC

-0.63

POSITIVE LOGITS

 gland

0.81

 glands

0.75

clinton

0.73

ksh

0.72

ng

0.71

 Phant

0.68

ansas

0.68

pillar

0.62

ussia

0.62

abama

0.62

Activations Density 0.048%

terms related to medical conditions and anatomy, focusing on words ending in "ary"

variations of the word "ary"

No Comments

No Known Activations