INDEX

Explanations

phrases related to movement, particularly focusing on living things or objects that are able to move

oai_token-act-pair · gpt-3.5-turbo

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

ingen

-0.67

inges

-0.66

ihil

-0.65

bryce

-0.65

nect

-0.65

omial

-0.64

akening

-0.64

gins

-0.63

tek

-0.63

ingo

-0.63

POSITIVE LOGITS

 forward

0.99

peed

0.91

 toward

0.89

 towards

0.86

objects

0.85

 cursor

0.84

 swiftly

0.83

 smoothly

0.83

abouts

0.82

 sideways

0.80

Activations Density 0.066%

phrases related to movement, particularly focusing on living things or objects that are able to move

No Comments

No Known Activations