INDEX

Explanations

occurrences of actions being taken or events happening

oai_token-act-pair · gpt-3.5-turbo

references to formal announcements or documents related to events or gatherings

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

 Units

-0.89

 Gleaming

-0.77

 acquisitions

-0.74

 transformations

-0.72

 Numbers

-0.71

 Levels

-0.71

 Monsters

-0.70

 fractions

-0.69

 Passive

-0.69

 verbs

-0.68

POSITIVE LOGITS

ritten

0.92

itialized

0.91

agraph

0.83

pload

0.82

 underway

0.80

emaker

0.78

ugi

0.78

ģ«

0.76

berra

0.76

 ensued

0.75

Activations Density 0.462%

occurrences of actions being taken or events happening

references to formal announcements or documents related to events or gatherings

No Comments

No Known Activations