INDEX

Explanations

phrases related to a variety or selection of items or options

oai_token-act-pair · gpt-3.5-turbo

instances of the word "range" indicating various types of ranges or scopes

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

der

-0.69

Ð²

-0.66

rics

-0.65

GBT

-0.64

AFTA

-0.63

hoc

-0.63

äºĶ

-0.63

Hub

-0.63

mit

-0.62

Fe

-0.61

POSITIVE LOGITS

 Rover

1.19

finder

1.15

 ranges

0.94

range

0.91

 range

0.86

ahead

0.81

ranging

0.74

ollah

0.70

onet

0.70

 Range

0.69

Activations Density 0.021%

phrases related to a variety or selection of items or options

instances of the word "range" indicating various types of ranges or scopes

No Comments

No Known Activations