INDEX

Explanations

verbs relating to successful achievement or accomplishment

oai_token-act-pair · gpt-3.5-turbo

phrases related to achieving goals or accomplishments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istries

-0.77

ĪĴ

-0.62

inders

-0.61

sit

-0.60

 humble

-0.60

nom

-0.59

 runway

-0.58

atro

-0.58

 slime

-0.57

pop

-0.57

POSITIVE LOGITS

>]

0.94

||||

0.82

ãĤ´

0.76

Interstitial

0.75

umerable

0.72

hyde

0.70

pez

0.70

 Measure

0.68

by

0.68

 Procedure

0.67

Activations Density 0.248%

verbs relating to successful achievement or accomplishment

phrases related to achieving goals or accomplishments

No Comments

No Known Activations