INDEX

Explanations

words related to cancellation or terminating events

oai_token-act-pair · gpt-3.5-turbo

terms related to cancellations

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

ocene

-0.80

artisan

-0.77

rity

-0.76

Redd

-0.72

METHOD

-0.70

deep

-0.70

adr

-0.69

Sense

-0.69

Appearance

-0.67

olds

-0.66

POSITIVE LOGITS

 cancell

0.90

 cancel

0.88

 cance

0.87

 screenings

0.80

uating

0.80

 canceled

0.79

 pregnancies

0.78

uate

0.78

ulum

0.77

uates

0.77

Activations Density 0.022%

words related to cancellation or terminating events

terms related to cancellations

No Comments

No Known Activations