INDEX

Explanations

words related to a specific type of cereal

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "corn" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Lumpur

-0.63

 Norn

-0.63

 consensual

-0.62

 feasibility

-0.61

ENA

-0.60

 Guild

-0.59

 Mons

-0.58

 Cheong

-0.57

 meanings

-0.57

Zel

-0.57

POSITIVE LOGITS

elia

1.16

meal

1.13

bread

1.13

flower

1.08

rows

1.05

hus

1.04

flake

1.03

nect

0.97

uc

0.94

fed

0.93

Activations Density 0.022%

words related to a specific type of cereal

occurrences of the word "corn" and its variations

No Comments

No Known Activations