INDEX

Explanations

references to the concept of "golden" or things associated with gold

oai_token-act-pair · gpt-3.5-turbo

references to the term "golden."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Cosponsors

-0.82

SPONSORED

-0.82

 Advertisement

-0.81

tics

-0.80

VICE

-0.78

ettings

-0.78

went

-0.75

DAQ

-0.72

Newsletter

-0.71

chens

-0.71

POSITIVE LOGITS

 golden

1.01

 calf

1.00

 maiden

0.86

 lion

0.82

 goose

0.81

 retri

0.81

ritional

0.80

 brown

0.80

ocious

0.79

 crispy

0.78

Activations Density 0.006%

references to the concept of "golden" or things associated with gold

references to the term "golden."

No Comments

No Known Activations