INDEX

Explanations

keywords related to molds and molds in various contexts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

tein

-0.69

cknow

-0.66

ãĤ³

-0.66

 Loan

-0.61

 Plan

-0.60

 FANTASY

-0.60

atre

-0.60

 Courts

-0.59

GH

-0.59

ZE

-0.59

POSITIVE LOGITS

ering

1.15

ovan

1.09

ings

0.88

ered

0.84

 spores

0.82

erer

0.80

erers

0.80

en

0.78

erella

0.77

 mold

0.76

Activations Density 0.123%

keywords related to molds and molds in various contexts

No Comments

No Known Activations