INDEX

Explanations

proper nouns, specifically names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or notable personalities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Hoff

-0.76

hess

-0.73

 Traps

-0.72

assian

-0.71

ammy

-0.69

zn

-0.68

 Nare

-0.67

 Whale

-0.67

 Related

-0.66

 Plays

-0.66

POSITIVE LOGITS

wayne

0.89

ãĥĩ

0.86

terday

0.75

ModLoader

0.73

bing

0.72

ku

0.72

ilater

0.71

itive

0.71

 repentance

0.70

acters

0.69

Activations Density 0.024%

proper nouns, specifically names

references to specific individuals or notable personalities

No Known Activations