INDEX

Explanations

phrases related to the passing of time and actions or achievements accomplished within that time period

oai_token-act-pair · gpt-3.5-turbo

utterances involving the verb "have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Apart

-0.67

 Anyway

-0.57

 magnification

-0.56

 Lens

-0.55

 Canal

-0.55

 Useful

-0.55

acle

-0.55

lighting

-0.54

 monog

-0.54

 Door

-0.54

POSITIVE LOGITS

 been

1.34

been

1.18

 become

1.17

 undergone

1.06

 begun

1.03

 gotten

1.01

 struggled

1.01

 risen

1.00

 emerged

0.98

 benefited

0.97

Activations Density 0.359%

phrases related to the passing of time and actions or achievements accomplished within that time period

utterances involving the verb "have" in various contexts

No Comments

No Known Activations