INDEX

Explanations

words related to the speed or rate of something

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "pace" or speed in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oral

-0.82

reditary

-0.81

oras

-0.79

ndum

-0.74

aina

-0.74

inals

-0.72

roma

-0.71

aida

-0.71

rador

-0.71

arij

-0.70

POSITIVE LOGITS

 pace

0.89

llor

0.84

ometer

0.82

 tempo

0.77

here

0.77

heet

0.75

uality

0.75

sheet

0.75

 paced

0.74

 cooker

0.73

Activations Density 0.020%

words related to the speed or rate of something

phrases related to the concept of "pace" or speed in various contexts

No Comments

No Known Activations