INDEX

Explanations

keywords related to peaks or high points in a sequence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating peak or high points in various contexts

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

acea

-0.77

 Cosponsors

-0.73

imei

-0.69

eeper

-0.69

-0.67

sbm

-0.67

ÄŁ

-0.65

Ã±o

-0.65

 alone

-0.64

rote

-0.64

POSITIVE LOGITS

agall

0.78

 unbeliev

0.75

 tensions

0.75

 popularity

0.75

ulic

0.74

 adolescence

0.73

 lows

0.73

 notoriety

0.71

 peac

0.71

 peaks

0.70

Activations Density 0.106%

keywords related to peaks or high points in a sequence

phrases indicating peak or high points in various contexts

No Comments

No Known Activations