INDEX

Explanations

mentions of the word 'pilot'

oai_token-act-pair · gpt-3.5-turbo

references to pilots and pilot programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

upon

-0.82

eners

-0.70

Brexit

-0.69

âĸº

-0.69

FORE

-0.67

TOP

-0.67

 Machina

-0.66

Else

-0.66

 Debor

-0.65

roots

-0.65

POSITIVE LOGITS

wings

0.96

 pilot

0.89

 Pilot

0.80

ilot

0.77

bach

0.76

isode

0.76

matically

0.75

imum

0.74

cies

0.74

 practition

0.73

Activations Density 0.026%

mentions of the word 'pilot'

references to pilots and pilot programs

No Comments

No Known Activations