INDEX

Explanations

phrases related to a specific location or time period

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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

asters

-0.80

ormons

-0.76

rior

-0.73

boards

-0.70

ciples

-0.68

 Ness

-0.64

icons

-0.64

Pwr

-0.64

Guard

-0.64

ilities

-0.62

POSITIVE LOGITS

 fateful

1.11

 particular

1.09

 same

1.01

 pesky

0.97

 kind

0.86

 sort

0.86

 awful

0.79

 regard

0.79

 aforementioned

0.77

cher

0.76

Activations Density 0.092%

phrases related to a specific location or time period

the word "that" in various contexts

No Comments

No Known Activations