INDEX

Explanations

the name "Boris"

oai_token-act-pair · gpt-3.5-turbo

references to specific political figures, particularly Boris and Nad

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

prise

-0.76

 Fargo

-0.75

adelphia

-0.69

lear

-0.69

overy

-0.68

gling

-0.67

ERA

-0.67

esley

-0.66

apsed

-0.66

prises

-0.65

POSITIVE LOGITS

vich

0.85

lav

0.82

anian

0.80

hin

0.79

illion

0.79

etr

0.78

 Kahn

0.78

ques

0.78

quet

0.77

etric

0.74

Activations Density 0.052%

the name "Boris"

references to specific political figures, particularly Boris and Nad

No Comments

No Known Activations