INDEX

Explanations

titles of movies, TV shows, and games

oai_token-act-pair · gpt-3.5-turbo

references to popular movies and television shows

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

istrate

-0.83

 stakeholders

-0.76

 listeners

-0.75

 regulator

-0.75

 knowledgeable

-0.75

verb

-0.74

agents

-0.72

irection

-0.71

informed

-0.68

igent

-0.68

POSITIVE LOGITS

etc

1.07

etc

1.02

whatever

0.89

 Guant

0.84

 Rhodes

0.80

 Odyssey

0.80

 Notting

0.78

 Baal

0.77

 Libya

0.77

JFK

0.77

Activations Density 0.318%

titles of movies, TV shows, and games

references to popular movies and television shows

No Comments

No Known Activations