INDEX

Explanations

phrases related to actions or events described in a formal or professional context

oai_token-act-pair · gpt-3.5-turbo

key terms related to significant events or topics across various domains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 aven

-0.77

 gren

-0.75

 gastro

-0.72

 assembly

-0.71

 arts

-0.71

 crest

-0.70

 rampant

-0.69

 agriculture

-0.69

 dart

-0.68

 disg

-0.67

POSITIVE LOGITS

 Needs

1.29

 Away

1.28

 Functions

1.26

 Approach

1.26

 Affect

1.26

 Costs

1.25

 Makes

1.24

 Ahead

1.24

 Relationship

1.24

 Definition

1.23

Activations Density 0.498%

phrases related to actions or events described in a formal or professional context

key terms related to significant events or topics across various domains

No Comments

No Known Activations