INDEX

Explanations

proper nouns related to the "Star Wars" series

oai_token-act-pair · gpt-3.5-turbo

references to the term "Phantom" in various contexts

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

references to "The Phantom"

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gewater

-0.81

HCR

-0.79

ells

-0.72

upon

-0.72

UTERS

-0.71

tics

-0.69

perature

-0.68

minist

-0.68

say

-0.68

enced

-0.67

POSITIVE LOGITS

 Orchestra

0.88

 Phantom

0.87

antom

0.82

 Thieves

0.77

 squid

0.77

 Chaser

0.76

 Horse

0.76

hawk

0.74

 Stranger

0.74

 Breaker

0.73

Activations Density 0.014%

proper nouns related to the "Star Wars" series

references to the term "Phantom" in various contexts

references to "The Phantom"

No Comments

No Known Activations