INDEX

Explanations

specific dates and time-related phrases

oai_token-act-pair · gpt-3.5-turbo

elements of time and setting in narratives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

notations

-0.80

 thinner

-0.68

icons

-0.66

inventoryQuantity

-0.65

 guarantees

-0.64

 appreciated

-0.62

 shred

-0.61

 meanings

-0.61

 emph

-0.61

ignt

-0.61

POSITIVE LOGITS

 Suppose

0.80

 Plaintiff

0.76

EGIN

0.76

 awoke

0.76

ezvous

0.73

 Suddenly

0.71

 approached

0.70

 brainstorm

0.69

 woke

0.69

 awoken

0.68

Activations Density 1.241%

specific dates and time-related phrases

elements of time and setting in narratives

No Comments

No Known Activations