INDEX

Explanations

phrases related to length, duration, or extension

oai_token-act-pair · gpt-3.5-turbo

references to "long" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 GEAR

-0.77

ģ«

-0.70

 Gleaming

-0.69

 Cosponsors

-0.67

Cash

-0.67

kind

-0.65

selves

-0.64

Kind

-0.63

trak

-0.61

witch

-0.61

POSITIVE LOGITS

 ardu

0.80

(>

0.80

duration

0.75

 subsequ

0.73

 longest

0.71

ogene

0.67

 duration

0.67

 stint

0.67

 slee

0.66

iameter

0.66

Activations Density 0.169%

phrases related to length, duration, or extension

references to "long" in various contexts

No Comments

No Known Activations