INDEX

Explanations

phrases related to the magnitude or extent of something

oai_token-act-pair · gpt-3.5-turbo

adjectives that express varying degrees of magnitude or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ools

-0.63

ortment

-0.59

tein

-0.59

elf

-0.58

hemy

-0.58

ogie

-0.56

arlane

-0.55

irit

-0.55

uddin

-0.54

 unsuspecting

-0.53

POSITIVE LOGITS

 enough

1.10

 compared

0.99

enough

0.88

0.80

 indeed

0.79

 owing

0.77

ly

0.77

ened

0.77

0.75

aneously

0.72

Activations Density 0.223%

phrases related to the magnitude or extent of something

adjectives that express varying degrees of magnitude or significance

No Comments

No Known Activations