INDEX

Explanations

years mentioned in a sentence

oai_token-act-pair · gpt-3.5-turbo

references to specific years and future timelines

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

 lately

-0.72

edIn

-0.71

 knack

-0.65

 recent

-0.64

 scorn

-0.63

 raged

-0.62

 hated

-0.62

 yesterday

-0.61

 fumble

-0.61

¬¼

-0.61

POSITIVE LOGITS

 onwards

0.87

ãĥ¯

0.79

 hopefully

0.75

0.71

 whichever

0.69

.''.

0.68

 unless

0.68

.ãĢį

0.67

Activations Density 0.172%

years mentioned in a sentence

references to specific years and future timelines

No Comments

No Known Activations