INDEX

Explanations

mentions of movies and television shows

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rade

-0.78

fax

-0.77

 voluntarily

-0.75

ESA

-0.71

 thereby

-0.70

ï¿½ï¿½ï¿½ï¿½

-0.69

 complying

-0.67

anooga

-0.67

India

-0.67

Iterator

-0.67

POSITIVE LOGITS

 aforementioned

1.25

 storyline

1.15

 soundtrack

1.12

 latter

1.11

 entirety

1.08

 protagonist

1.07

 screenplay

1.06

 narrator

1.04

 anthology

1.03

 narration

1.03

Activations Density 0.659%

mentions of movies and television shows

instances of the word "the"

No Comments

No Known Activations