INDEX

Explanations

keywords related to a specific time period or situation, particularly with phrases containing the word "during this"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "this" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

cks

-0.73

isms

-0.72

witz

-0.72

esm

-0.70

asures

-0.70

adle

-0.69

ãĥĺ

-0.68

masters

-0.68

ãĤ¹ãĥĪ

-0.68

POSITIVE LOGITS

 particular

1.11

 week

0.95

 weekend

0.87

 latest

0.87

 year

0.86

 month

0.86

 morning

0.86

 newfound

0.85

 afternoon

0.85

 article

0.82

Activations Density 0.203%

keywords related to a specific time period or situation, particularly with phrases containing the word "during this"

mentions of the word "this" in various contexts

No Comments

No Known Activations