INDEX

Explanations

words related to automation or automatic processes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "automatically."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.85

ergus

-0.81

tons

-0.74

,,,,

-0.74

andals

-0.73

ador

-0.72

 Emin

-0.70

 Mouth

-0.70

 VIDEOS

-0.69

borough

-0.68

POSITIVE LOGITS

immune

0.86

 assume

0.82

 migrate

0.81

 induct

0.81

 detect

0.80

 populate

0.79

 identifiable

0.78

 revert

0.77

 terminate

0.76

 recognize

0.75

Activations Density 0.027%

words related to automation or automatic processes

occurrences of the word "automatically."

No Comments

No Known Activations