INDEX

Explanations

the word "things" in sentences

oai_token-act-pair · gpt-3.5-turbo

references to "things" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bern

-0.73

iary

-0.71

ECD

-0.66

HOU

-0.66

strom

-0.64

DOM

-0.63

sylv

-0.63

adia

-0.63

ISSION

-0.62

geon

-0.62

POSITIVE LOGITS

 happening

0.97

 happen

0.96

 happens

0.90

 happened

0.89

 happ

0.85

 transpired

0.74

 Happ

0.70

 pertaining

0.70

 things

0.68

omething

0.68

Activations Density 0.037%

the word "things" in sentences

references to "things" in various contexts

No Comments

No Known Activations