INDEX

Explanations

references to the use of force or influence in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to the use of force, influence, and methods 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 subsequ

-0.75

ilogy

-0.74

icipated

-0.71

ufact

-0.69

ategories

-0.69

irement

-0.68

bernatorial

-0.68

ortal

-0.66

ģĸ

-0.65

urd

-0.64

POSITIVE LOGITS

 sparing

0.88

 levers

0.76

 wisely

0.75

 interchange

0.71

 analogy

0.70

 tools

0.70

onyms

0.67

 extensively

0.66

 liber

0.65

 APIs

0.65

Activations Density 0.363%

references to the use of force or influence in various contexts

terms related to the use of force, influence, and methods in various contexts

No Comments

No Known Activations