INDEX

Explanations

mentions of different beverages, especially types of drinks like coffee, tea, wine, and more

oai_token-act-pair · gpt-3.5-turbo

references to beverages, particularly in a social context

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

çīĪ

-0.79

Reviewer

-0.76

iets

-0.75

abilities

-0.75

ahime

-0.75

ĸļ

-0.73

indu

-0.73

omnia

-0.72

nw

-0.72

notations

-0.68

POSITIVE LOGITS

 groceries

0.84

 assorted

0.80

 freshly

0.79

milo

0.75

 noodles

0.74

tea

0.72

 champagne

0.72

 potato

0.72

 wine

0.72

 disinfect

0.72

Activations Density 0.099%

mentions of different beverages, especially types of drinks like coffee, tea, wine, and more

references to beverages, particularly in a social context

No Comments

No Known Activations