INDEX

Explanations

terms related to the beginning or starting point of a process or event

oai_token-act-pair · gpt-3.5-turbo

references to the word "initial" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

yers

-0.73

Nature

-0.73

rom

-0.70

ifling

-0.69

rf

-0.69

cig

-0.66

âĹ¼

-0.66

gans

-0.66

=-=-=-=-=-=-=-=-

-0.65

Across

-0.64

POSITIVE LOGITS

 stages

0.98

aneously

0.89

 phases

0.88

isations

0.85

izations

0.84

 impressions

0.83

 foray

0.83

 disclaimer

0.82

izers

0.82

 impulse

0.81

Activations Density 0.011%

terms related to the beginning or starting point of a process or event

references to the word "initial" in various contexts

No Comments

No Known Activations