INDEX

Explanations

genes and genetic terms

oai_token-act-pair · gpt-3.5-turbo

references to "gene" and related genetic terminology

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

ategory

-0.78

ango

-0.73

agher

-0.70

lain

-0.67

 Lanka

-0.67

aby

-0.67

deen

-0.66

isconsin

-0.66

akening

-0.66

izard

-0.65

POSITIVE LOGITS

alogy

1.48

alog

1.23

etics

1.13

etically

1.06

etic

0.96

esis

0.91

 mutation

0.77

 gene

0.74

plex

0.73

REE

0.73

Activations Density 0.021%

genes and genetic terms

references to "gene" and related genetic terminology

No Comments

No Known Activations