INDEX

Explanations

various possible explanations or options in a text

oai_token-act-pair · gpt-3.5-turbo

documents that explore various explanations, possibilities, or options for a given situation

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĪ

-0.73

umbai

-0.69

ãĥ©ãĥ³

-0.65

gian

-0.65

entimes

-0.60

iencies

-0.60

Content

-0.60

Beast

-0.60

phies

-0.60

enged

-0.59

POSITIVE LOGITS

 explanations

0.95

 besides

0.89

 whereby

0.89

 options

0.85

 involving

0.84

 imaginable

0.83

 alternatives

0.82

 available

0.82

 scenarios

0.82

 offered

0.80

Activations Density 0.183%

various possible explanations or options in a text

documents that explore various explanations, possibilities, or options for a given situation

No Comments

No Known Activations