INDEX

Explanations

phrases related to sports seasons and events

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

references to seasons, timelines, and deadlines

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

indu

-0.71

èª

-0.68

 Thiel

-0.66

encrypted

-0.65

thia

-0.65

istine

-0.65

Statement

-0.65

 Mellon

-0.65

uppet

-0.64

?????-

-0.64

POSITIVE LOGITS

 approaching

1.15

 winding

1.10

 wrapping

1.01

 officially

0.92

 underway

0.92

 drawing

0.91

 looming

0.90

 nearing

0.89

 ticking

0.87

 heating

0.84

Activations Density 0.200%

phrases related to sports seasons and events

references to seasons, timelines, and deadlines

No Known Activations