INDEX

Explanations

names or references to "Ki" with varying levels of importance or relevance

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual named Ki or variations of that name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

å£«

-0.85

urgy

-0.84

icity

-0.80

encers

-0.79

ica

-0.75

ãĤ¢ãĥ«

-0.73

ifiable

-0.73

arians

-0.73

å¥³

-0.72

*/(

-0.71

POSITIVE LOGITS

ombo

0.83

pee

0.81

allery

0.76

uchi

0.75

jing

0.74

ongyang

0.73

pling

0.73

hee

0.70

selage

0.70

wan

0.69

Activations Density 0.051%

names or references to "Ki" with varying levels of importance or relevance

references to a specific individual named Ki or variations of that name

No Comments

No Known Activations