INDEX

Explanations

specific named entities or proper nouns related to technology products

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" and its variations in various contexts

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

racial

-0.75

AIDS

-0.74

 Soros

-0.73

 UNCLASSIFIED

-0.71

ÃŃ

-0.70

claw

-0.70

 pursuant

-0.70

-0.69

.''

-0.68

leground

-0.68

POSITIVE LOGITS

 cheapest

1.22

 simplest

1.16

 latest

1.16

 aforementioned

1.16

 coolest

1.16

 easiest

1.15

 biggest

1.14

 smallest

1.12

 latter

1.11

 lowest

1.08

Activations Density 0.640%

specific named entities or proper nouns related to technology products

occurrences of the word "the" and its variations in various contexts

No Comments

No Known Activations