INDEX

Explanations

examples of items that are adaptable or have various applications

oai_token-act-pair · gpt-3.5-turbo

terms related to versatility and adaptability

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iquette

-0.75

light

-0.74

omen

-0.71

©¶æ

-0.71

 Regulatory

-0.70

 Insider

-0.68

Fed

-0.68

eln

-0.67

ween

-0.67

uthor

-0.66

POSITIVE LOGITS

theless

1.06

 versatile

0.89

 versatility

0.83

 minded

0.74

isable

0.73

 modular

0.72

 reversible

0.71

 portable

0.71

 slic

0.70

ength

0.69

Activations Density 0.034%

examples of items that are adaptable or have various applications

terms related to versatility and adaptability

No Comments

No Known Activations