INDEX

Explanations

titles of movies or series featuring keywords such as "The" or character names

oai_token-act-pair · gpt-3.5-turbo

titles of movies or media within content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï¿½ï¿½ï¿½ï¿½

-0.71

/>

-0.67

 patiently

-0.66

poke

-0.66

 according

-0.66

gpu

-0.66

 conced

-0.65

ement

-0.65

 concede

-0.65

enthal

-0.63

POSITIVE LOGITS

atre

1.21

oret

1.20

ories

1.09

resa

1.05

sis

1.04

mes

0.98

odor

0.97

 Basics

0.95

orem

0.94

odore

0.94

Activations Density 0.232%

titles of movies or series featuring keywords such as "The" or character names

titles of movies or media within content

No Comments

No Known Activations