INDEX

Explanations

phrases introducing a new topic or concept

oai_token-act-pair · gpt-3.5-turbo

assertions or statements beginning with "That."

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

natureconservancy

-0.75

"],"

-0.73

thro

-0.70

emis

-0.68

hips

-0.65

vre

-0.62

rior

-0.60

uty

-0.59

atur

-0.59

ogly

-0.59

POSITIVE LOGITS

cher

0.90

 mattered

0.84

 culminated

0.81

 includes

0.76

 same

0.76

 sounds

0.75

 pesky

0.75

 fateful

0.75

 translates

0.75

 begs

0.74

Activations Density 0.098%

phrases introducing a new topic or concept

assertions or statements beginning with "That."

No Comments

No Known Activations