INDEX

Explanations

words related to the act of execution

oai_token-act-pair · gpt-3.5-turbo

references to executions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ijn

-0.79

 Lanka

-0.72

landers

-0.68

 Soda

-0.67

 Tire

-0.67

thora

-0.67

IGH

-0.65

é¾įå

-0.65

 Acid

-0.64

 Lank

-0.64

POSITIVE LOGITS

eering

0.80

 execute

0.76

locks

0.76

 executes

0.75

eers

0.75

 executed

0.74

ution

0.74

 execution

0.73

 executions

0.71

sequence

0.70

Activations Density 0.047%

words related to the act of execution

references to executions

No Comments

No Known Activations