INDEX

Explanations

references to time or duration

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate possession or experience

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

 Pair

-0.66

 Lands

-0.62

/+

-0.59

Else

-0.59

 Kills

-0.58

 Apart

-0.57

 uproar

-0.56

 clicks

-0.56

manac

-0.54

itability

-0.54

POSITIVE LOGITS

 been

1.46

been

1.38

 gotten

1.31

 risen

1.13

 undergone

1.11

 taken

1.11

 benefited

1.10

 fallen

1.08

 gone

1.08

 Been

1.08

Activations Density 0.391%

references to time or duration

phrases that indicate possession or experience

No Comments

No Known Activations