INDEX

Explanations

phrases related to preparation or readiness

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prepare" and its variations, indicating readiness or planning for an event or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

holes

-0.78

ochet

-0.68

 penny

-0.63

ignment

-0.63

hole

-0.62

enez

-0.61

 kindred

-0.61

volent

-0.60

 traffickers

-0.59

=-=-=-=-=-=-=-=-

-0.58

POSITIVE LOGITS

itude

0.84

 beforehand

0.80

 Statements

0.78

Statement

0.75

folios

0.75

 meals

0.73

oster

0.71

 prepare

0.70

 ahead

0.70

itud

0.70

Activations Density 0.028%

phrases related to preparation or readiness

instances of the word "prepare" and its variations, indicating readiness or planning for an event or action

No Comments

No Known Activations